[Objective] With the increasing proportion of new energy, traditional grid-following (GFL) control based on phase-locked loop (PLL) synchronization gradually exhibits inherent stability limitations in weak grid conditions. Meanwhile, grid-forming (GFM) control with self-synchronizing source characteristics has emerged as a hot solution. However, existing research predominantly focuses on the voltage regulation or synchronization stability of GFM control, with less attention to its frequency modulation capability and characteristics. [Methods] This paper systematically reviewed four mainstream GFM control methods, including droop control, virtual synchronous generator (VSG) control, matching control, and virtual oscillator control (VOC), explained their frequency modulation principles, and analyzed their advantages and disadvantages from the aspects of the control loop and application scenarios. On this basis, a grid-connected simulation model for new energy systems was built to conduct a simulation-based analysis of the frequency modulation response characteristics of different kinds of frequency modulation control across diverse scenarios. Finally, this study summarized challenges of GFM control in strategy optimization, parameter tuning, and multi-unit coordination, with the future development prospects pointed out. [Results] Droop control regulates the active power of generating units by responding to system frequency deviations, featuring advantages of the simple structure and strong grid strength adaptability. However, its lack of inertia support results in relatively weaker frequency modulation performance. On the basis of droop control, VSG control simulates the inertia response characteristics of conventional synchronous machines and can better suppress the change performance of system frequency. However, it faces challenges in parameter tuning, fault ride-through, and multi-unit coordination. Matching control utilizes the dynamic characteristics of DC capacitors to simulate the inertia properties of traditional synchronous machines and thus restrain change performance of system frequency, but it fails to provide sustained support in the frequency quasi-steady state. VOC generates frequency responses similar to droop control via oscillator dynamic equations that directly govern amplitude and frequency. However, it is difficult for its high output harmonics to satisfy grid connection requirements. [Conclusion] Virtual synchronous machine control has become the most promising research direction in GFM control due to its technical advantages of balancing frequency modulation performance and strong grid strength adaptability in participating in system frequency modulation. However, technical challenges including synchronization stability, fault ride-through, and coordinated control need to be tackled. In the future, in-depth research should be conducted on control strategies and parameter optimization, and multi-unit collaborated control to facilitate the large-scale application of GFM control.

[Objective] With the widespread integration of distributed energy, the complex topology and exponentially increased monitoring data of distribution networks pose new challenges to fault diagnosis. Traditional fault diagnosis methods mainly rely on monitoring data and human experience. With the rapid development of cloud computing and communication technology, artificial intelligence methods are widely applied in the field of fault diagnosis. However, existing artificial intelligence methods have a high dependence on training data, requiring a large number of basic data as support. Therefore, an intelligent fault diagnosis method for distribution networks was proposed by leveraging digital twin technology to improve the efficiency and accuracy of fault diagnosis. [Methods] A digital twin of the distribution network was constructed using digital twin technology, and virtual diagnosis results were used to guide actual system operation. Additionally, wavelet packet decomposition was utilized to obtain the energy of each frequency band of the signal to construct feature vectors, which were input into the improved convolutional autoencoder (CAE) model for learning to identify the fault type. The digital twin system included a physical layer, a data layer, a model layer, and a service layer, achieving virtual-real mapping, with the virtual twin reflecting the state of the physical entity in real time. In the simulation experiment, the three-port ring network structure of a 10 kV distribution network in an area was used as the basis, and a complete experimental dataset was constructed, including 7 520 pieces of normal and fault sample data. [Results] The performance analysis results of the proposed model show that after 100 iterations of training, the diagnostic accuracy of the improved CAE model is close to 0.98. Moreover, the intelligent diagnosis results of the digital twin system demonstrate that the fault types diagnosed by the proposed method are basically consistent with the actual fault types, and for five common fault types, it maintains an ideal diagnostic accuracy. The average accuracy reaches 0.95, and the diagnosis time is only 5.39 s. A comparison of diagnoses using different methods indicates that the proposed method has a higher diagnostic accuracy. [Conclusion] The application of digital twin technology to the intelligent fault diagnosis of distribution networks, by adopting the approach of virtual-real integration, further improves the accuracy and real-time performance of fault diagnosis, thus providing a new technical means for the intelligent fault diagnosis of distribution networks. This contributes to enhancing the reliability and safety of distribution networks and holds important theoretical and practical value for the development of smart grids. Furthermore, future research will focus on how to cope with the changes in the structure of distribution networks to improve the applicability of the proposed fault diagnosis method.

[Objective] Accurate electric load forecasting is the key to the smooth operation and effective management of power systems, which can enable power companies to effectively dispatch power generation equipment, thereby improving their operational efficiency and economic benefits. However, electric load data are affected by a variety of external factors and have significant time dependence, which makes their accurate prediction difficult. Therefore, an electric load forecasting model combining multi-factor modeling and time series analysis was proposed, which taking into account the analysis of the complex influences of multiple factors and the time dependence characteristics of electric load, so as to realize accurate electric load forecasting. [Methods] To break through the respective limitations of multi-factor analysis methods and time series forecasting modeling methods, an improved electric load forecasting model combining long short-term memory (LSTM) network and Bayesian optimization algorithm was proposed with the help of deep learning and a multi-factor analysis method. Firstly, a comprehensive multi-factor feature pool was constructed, including the historical time series features of electric load and a variety of external factors to fully capture the complex relationships between electric load data and multiple influencing factors. Secondly, the LSTM network was used as the core model, and its unique gating mechanism and memory unit were used to capture the time dependence of electric load data and the complex association between multiple factors. The Bayesian optimization algorithm was introduced to tune the hyperparameters of the LSTM model, and the Gaussian process was used as the surrogate model to make full use of the prior information to improve the training efficiency and prediction performance of the model. [Results] Five real transformer datasets were used to train and test the model. The effectiveness of the model was verified by several evaluation indicators. The proposed electric load forecasting method based on multi-factor feature engineering modeling has significantly better prediction performance than the model using only a single factor for forecasting on five different transformer datasets, which further highlights the effectiveness of the multi-factor feature pool. The maximum coefficient of determination of the LSTM model is 0.920 7, and the minimum mean square error and the minimum mean absolute error are 0.042 and 0.024, respectively. The results demonstrate the superior performance of the proposed method in complex electric load forecasting tasks. [Conclusion] The electric load forecasting model combining multi-factor modeling and time series analysis fully considers the complexity of external factors and the time dependence characteristics of electric load and innovatively introduces a comprehensive feature pool to participate in LSTM model training and testing. The LSTM network combined with multi-factor feature pool modeling has high prediction accuracy and robustness, which provides a new technical idea for electric load forecasting, has important reference value for the planning and dispatch of smart grid, and lays a foundation for further development of accurate load forecasting technology.

[Objective] 304 stainless steel is a chromium-nickel stainless steel with austenite as the main crystal structure. It is widely used in the aerospace, marine, and chemical industries for its excellent heat and corrosion resistance. However, its hardness is low, and its cavitation erosion resistance is poor. When it is used as a material for turbine blades, exposure to complex environmental conditions leads to surface pitting and spalling, which severely shortens the service life of the blades. [Methods] To enhance the service life of 304 stainless steel, a novel iron-based alloy cladding layer was fabricated on its surface by using laser cladding. The obtained iron-based alloy cladding layer was subjected to phase analysis, microstructural observation, EBSD analysis, hardness testing, and cavitation erosion testing to analyze its phase composition, crystallographic characteristics, microhardness, and cavitation erosion resistance. [Results] The results show that the iron-based alloy cladding layer is mainly composed of α-Fe phase and Cr₂₃C₆ phase. The cladding layer has good forming quality without microcracks and with only a few pores. The microstructure of the cladding layer shows typical non-equilibrium solidification structure characteristics, which is composed of dendrites and interdendritic network structures, showing the morphologies of planar crystals, cellular crystals, columnar crystals, and equiaxed crystals from the bottom region to the top region. The EBSD results show that high-density grain boundaries were formed in the cladding layer and no obvious texture was formed. The cross-sectional microhardness of the cladding layer fluctuates between 640 HV_0.2 and 750 HV_0.2, which is considerably higher than the microhardness of the 304 substrate (187.6 HV_0.2). The higher microhardness of the cladding layer is attributed to solid solution strengthening, the second phase strengthening by Cr₂₃C₆ and Cr₇C₃ hard phases distributed among cellular dendrites, and grain boundary strengthening brought by high-density grain boundaries. The cumulative mass losses of the 304 substrate and the iron-based alloy cladding layer after cavitation erosion test for 300 min are 24.8 mg and 7.8 mg, respectively. The mass loss of the iron-based alloy cladding layer is about 31.5％ of that of the 304 substrate. During the whole cavitation erosion test, the cumulative mass loss of the iron-based alloy cladding layer is less than that of the 304 substrate. The surface analysis results after the cavitation erosion test show that the shear waves generated by the collapse of bubbles can cause stress accumulation on the surface of the material, thereby promoting the formation of slip bands. Cracks are prone to generation and expansion on the slip bands, eventually leading to material spalling and forming cavitation pits. Small grain sizes, a high grain boundary density, and high microhardness are the key reasons for the excellent cavitation erosion resistance of the cladding layer. [Conclusion] The higher microhardness of iron-based alloy cladding layer significantly improves the cavitation erosion resistance of the 304 stainless steel substrate. In this study, a high-microhardness iron-based alloy cladding layer for surface modification of 304 stainless steel was designed and prepared to promote the application of laser cladding technology in the reinforced coatings for turbine blade surfaces to a certain extent.

[Objective] In mobile edge computing (MEC) systems in dynamic environments, traditional task offloading strategies generally have problems such as inflexible scheduling, weak adaptability to environmental changes, and limited delay control capabilities, making it difficult to meet the processing requirements of delay-sensitive tasks. To this end, this paper proposed a MEC offloading optimization method that integrated unmanned aerial vehicle (UAV)-assisted mechanisms to improve the system′s service quality and task response efficiency. [Methods] Considering the dynamic user distribution and frequent link state fluctuations in UAV-MEC scenarios, this paper jointly modeled task offloading, user scheduling, and UAV trajectory control as a Markov decision process (MDP), and used the deep Q-network (DQN) framework to learn approximate optimal strategies. In state modeling, factors such as UAV energy consumption constraints, user task attributes, and timeliness requirements were fully considered, with action space discretization implemented to adapt to the DQN architecture. The reward function introduced delay loss and timeout penalty mechanisms to guide the agent in adaptively learning effective offloading strategies. [Results] The simulation results show that the proposed method is superior to the benchmark strategies such as full local computing and full edge offloading in terms of cumulative rewards, average task processing delay, and the number of task timeout penalties, showing good strategy convergence and environmental adaptability, especially when the communication link fluctuates or computing resources are limited. [Conclusions] The proposed DQN-based UAV-assisted edge computing joint optimization strategy can significantly improve the system′s processing efficiency and scheduling performance for time-sensitive tasks in a dynamic and complex environment, providing a feasible method path and theoretical support for the design and optimization of high-mobility mobile edge computing systems.

[Objective] Rice husk ash (RHA), as bulk agricultural waste generated during rice processing, has been increasing in annual production with the growth of global rice consumption. The use of RHA as a supplementary cementitious material for concrete can significantly reduce carbon emissions during concrete production by replacing part of cement and also effectively improve the durability and mechanical properties of concrete, which is in line with the demand for sustainable development of the construction industry. However, the durability of RHA concrete is influenced by a number of factors such as particle size distribution, concrete mix design, and curing conditions. Existing studies are fragmented and lack a systematic performance evaluation framework and optimization design strategy. Therefore, this study aims to review the durability of RHA concrete, analyze the mechanism and influencing factors of its deterioration resistance, and provide theoretical support for the development of application standards and breakthroughs in promotion bottlenecks, so as to promote its wide application in green building materials. [Methods] The focus of this study was the durability of RHA concrete, and the research progress on its shrinkage, carbonation resistance, chloride penetration resistance, acid resistance, freeze-thaw cycle resistance, and fire resistance was systematically investigated. The research included the analysis of the physicochemical properties of RHA (e.g., silica content, particle size, and volcanic ash activity) and investigation of the effects of different RHA contents and treatments (e.g., chemical activation, heat treatment, and wet curing) on the properties of concrete. In addition, the synergistic effects of RHA with other mineral admixtures (e.g., coal fly ash, slag, and metakaolin) and its optimization effect on durability were explored. [Results] After the various aspects of performances in the field of durability were sorted out and summarized, the corresponding research content and key technologies were summarized. It is found that RHA concrete has significant improvements in shrinkage inhibition, carbonation resistance, chloride penetration resistance, acid corrosion resistance, freeze-thaw cycle durability, and fire resistance. In addition, the systematic study concludes that RHA can achieve multi-dimensional enhancement of concrete durability performance, which aligns with the development needs of sustainable building materials. However, the engineering application of RHA concrete still faces multiple challenges: the quality difference of RHA due to the difference in raw material sources requires the establishment of strict control standards for activity index and particle size distribution; the sensitivity of alkali-silica reaction requires the precise control of RHA dosage and alkali content; the long wet curing period increases construction and time costs significantly. [Conclusion] Future research should focus on standardization of RHA quality, synergies with other mineral admixtures, innovative treatment methods, and monitoring of long-term performance to promote the widespread use of RHA concrete in construction and reduce the environmental impact of conventional cement.

[Objective] With the gradual improvement of requirements for motor energy efficiency grade, outer-rotor low-speed permanent magnet motors are widely used in the industrial field, due to their advantages of high torque density, high efficiency, and energy saving. To meet the working conditions of heavy-load start-up and long-term low-speed heavy-load operation of industrial sector, the design of outer-rotor low-speed permanent magnet motors is developing in the direction of improving motor torque density. Accordingly, the issue of high heat generation caused by the high torque density of motors is becoming a focus of research. [Methods] To address the problem of high temperature rise in outer-rotor low-speed permanent magnet motors under heavy-load operation conditions, this paper established the physical model of outer-rotor low-speed permanent magnet motors and calculated the distribution of motor losses. First, based on the basic theory of computational fluid dynamics, according to the heat source distribution and structural characteristics of outer-rotor low-speed permanent magnet motors, the study designed and installed axial and circumferential Z-shaped water-cooled structures in stator bracket near the inner surface of the stator core. The simulation model with water inlet and outlet at the motor bottom was also established. The flow field and temperature field of two water-cooled structures were simulated and analyzed using Fluent software. The circumferential Z-shape structure was determined as a more suitable water-cooled design structure. Second, by the calculation method coupling fluid flow and heat transfer, the temperature field of the motor equipped with a circumferential Z-shaped 9-channel water-cooled structure was analyzed using Fluent software. Whether the water-cooled structure meeting the heat dissipation requirements of the outer-rotor low-speed permanent magnet motors was verified with the maximum temperature of the permanent magnet and insulation. Finally, based on the theoretical analysis, this paper determined the factors influencing heat dissipation in water-cooled structures, including water channel number, cooling water flow rate, and radial width of water channel section. The influences of different factors on motor temperature rise were studied using Fluent software. [Results] The results indicate that the flow rate distribution of the circumferential Z-shaped water-cooled structure is more uniform with a smaller inlet and outlet pressure difference, which is more suitable for outer-rotor low-speed permanent magnet motors. As the number of water channels, cooling water flow rate, and radial width of water channel section increase, the heat dissipation is enhanced. However, after each factor reaches a certain value, the motor temperature tends to stabilize. According to the analysis results, the final design includes 7 water channels with a radial width of 17 mm and a cooling water flow rate of 0.5 m/s. [Conclusion] The research results can provide a theoretical basis for the application of water-cooled systems of outer-rotor low-speed permanent magnet motors in high-load working environments.

[Objective] To address the problems of traditional load forecasting methods, such as low information utilization efficiency, large errors, and difficulties in adapting to the diversity and randomness of actual power load changes, a power system load forecasting method based on land spatial information perception was proposed. This method could improve the accuracy and reliability of load forecasting, provide key data support for power system planning and construction, and meet the needs of economic and social development. [Methods] This algorithm adopted the strategy of classification by area with the use of urban land spatial information and power grid load data. For developed areas (with loads known), historical load data were used for curve fitting to carry out load forecasting. As for newly developed areas (with loads unknown), the average load density of the same land type in developed areas was used for equivalentprocessing to form the basic information of load forecasting, and then load forecasting was carried out. At the same time, this algorithm subdivided the historical load data and equivalent load data. The algorithm integratedthe exponential model, the growth curve model, and the elastic coefficient model and mainly used the combination of dynamic weights to form the best fitting scheme. Using the above methods, a power system load forecasting technology based on land spatial information perception was formed. The historical data from 2014 to 2020 were used as the benchmark for parameter fitting, and the historical load data of industrial power, residential power, commercial power, public facilities power, and other power types were sorted out. The load data of 2021 were taken as the forecasting object. The differences of the exponential model, the growth curve model, and the elastic coefficient model in total forecast and forecast based on classification by area were compared and analyzed through experiments. The results show that the forecasting accuracy based on classification by area is about 33% higher than that of total forecasting. On this basis, the best fitting effects based on dynamic weights and mean weights were compared and analyzed. The calculation results show that the best fitting forecasting error is only 1.12% when dynamic weights are used, which is 12% smaller than the forecasting error in the case of using mean weights. In conclusion, the scheme proposed can significantly improve the accuracy and reliability of load forecasting. [Results] The results of this paper show that the accuracy of the load forecasting model can be improved by using the method of classification by area to classify spatial information according to the land and load types. The algorithm has better dynamic adaptability by dynamically adjusting parameter weights and integrating single forecasting models, able to achieve the best fitting results and enhance forecasting accuracy. [Conclusion] The highlights of this paper are as follows. Firstly, the data processing method of classification by area is adopted to improve the utilization rate of spatial information and load information of the urban power grid. Secondly, the traditional load forecasting models are integrated by using dynamic weights, which breaks the limitations of single models. This algorithm further improves the accuracy and reliability of urban power grid load forecasting through the above two approaches.

[Objective] With the increasing demand for application of unmanned aerial vehicles (UAVs) in complex scenarios such as power grid inspection and emergency rescue, the limitations of single UAV in task execution have become increasingly prominent. Multi-UAV formation can effectively improve inspection efficiency and expand operation coverage, but significant challenges remain in formation maintenance, collaborative trajectory optimization, and environmental adaptability to complex environments during practical application. An optimal control method that integrated virtual spring forces with the hp-adaptive pseudospectral method was proposed to address the difficulties of formation maintenance and path optimization during large planar maneuvers of UAV swarms, thus enhancing the stability, flexibility, and disturbance resistance of collaborative flight of UAV formations and providing technical support for high-demand scenarios for UAVs such as power grid inspection. [Methods] First, a multi-UAV system dynamics model was built, and a virtual spring mechanism was incorporated into the formation control system to realize flexible constraints and elastic self-adjustment between UAVs. By combining the virtual spring method with the traditional leader-follower method, a formation strategy that could balance rigid support and adaptive adjustment ability of formations was designed. On this basis, the hp-adaptive pseudospectral method was then applied to solve the optimal control problem of UAV formations. By discretizing state and control variables at Legendre-Gauss nodes and constructing global interpolation polynomials, the trajectory optimization problem was transformed into a nonlinear programming (NLP) problem, with constraints such as dynamics, energy consumption, and velocity combined to conduct a high-precision numerical solution. In simulation experiments, a typical four-UAV diamond formation was set up, and the algorithm′s adaptability to different terrains, wind disturbances, and mission requirements was comprehensively explored. [Results] Simulation results show that the proposed virtual spring-based hp-adaptive pseudospectral method can realize smooth formation turning and velocity control. During a 90° large maneuver, UAVs can not only satisfy multiple constraints such as path deflection and speed change, but also maintain a stable formation. Compared with traditional leader-follower and artificial potential field methods, the new method demonstrates significant advantages in position error, formation maintenance, and wind resistance. Under 10m/s strong wind, the formation stability of the proposed method exceeds 70％, showing significant advantages over its competing algorithms. 3D terrain simulations and real flight tests further validate the algorithm′s adaptability and robustness, and the method still maintains lower formation deformation rates and trajectory tracking error under multiple terrains such as hills, mountains, and canyons, with the features of reasonable energy consumption control and strong engineering practicability. [Conclusion] By innovatively integrating the virtual spring elastic constraint with the hp-adaptive pseudospectral method, an optimal control technique for UAV formation trajectory planning in complex environments was proposed. The rigidity constraint limitations of traditional formation methods are overcome, flexible maintenance and adaptive adjustment of formations are realized, and the accuracy and efficiency of collaborative trajectory optimization are significantly improved by the method. The research results provide an efficient and reliable technical path for collaborative flight of UAV swarms in demanding tasks such as power grid inspection and emergency rescue. Future studies may further increase the method′s application potential in multi-formation collaboration and complex obstacle environments, promoting the intelligent and practical development of UAV formations.

[Objective] With the rapid development of artificial intelligence, object detection technology based on visible light images has become increasingly advanced and has been widely applied in fields such as autonomous driving, security monitoring, and intelligent transportation. However, in low-light scenes (such as nighttime or dimly lit environments), the performance of object detection algorithms based on visible light images decreases significantly. This is primarily due to severe information loss in visible light images under low-light conditions, making it difficult to extract target features. To solve this problem, multi-modal object detection technology combining visible light and infrared images was proposed, which could effectively enhance object detection performance in low-light scenes. However, the multi-modal method is costly and requires precise registration of images from different modalities, which increases system complexity and processing burden. In response, this study proposed an object detection network with infrared sensing (InSCnet), aimed at using a visible light camera to predict infrared thermal radiation characteristics, thus improving the network′s object detection capability in low-light scenes without increasing modality. [Methods] The InSCnet network used visible light images as input and generated infrared images through an infrared prediction branch (IPB), which predicted thermal radiation characteristics to enhance the network′s perception of low-light scenes. A complementary fusion filter (COFF) module was designed to effectively integrate multi-scale visual and thermal radiation features. By complementing these two features, the COFF module enhanced their mutual complementarity and avoided the network′s over-reliance on a single modality. In addition, a hybrid feature pyramid (HyFP) module was employed to further improve the fusion and extraction of multi-scale global and local features through feature pyramids and attention mechanisms, ensuring that the network maintained high detection accuracy under varying low-light conditions. [Results] Experimental results show that InSCnet performs excellently on the LLVIP pedestrian detection dataset, with S_mAP50 reaching 0.830 and S_mAP50-95 reaching 0.426. Moreover, experiments conducted on the DroneVehicle dataset show a S_mAP50 of 0.702, confirming its ability to handle multi-class low-light detection. [Conclusion] InSCnet improves object detection performance in low-light scenes by introducing infrared thermal radiation characteristics and a feature fusion mechanism. The network can effectively detect objects that are difficult to identify in visible light images under low-light conditions, providing an effective solution for object detection in such environments. Future research will further explore ways to optimize the network structure.

[Objective] With the rapid development of long-span suspension bridges, wind-induced vibration has gradually become a crucial factor affecting their safety and comfort. Small horizontal-axis wind turbines installed on bridges can not only effectively suppress vortex-induced vibration but also provide wind energy for powering ancillary facilities. However, the impact of small horizontal-axis wind turbines on bridges has not been comprehensively and systematically studied, especially their specific influence on bridge buffeting response. Therefore, this study aims to explore the influence of small horizontal-axis wind turbines on bridge buffeting response and assess the effects of different wind turbine layout schemes on bridge dynamic response, so as to provide a theoretical basis and practical guidance for control of wind-induced vibration of bridges by wind turbines. [Methods] This study took the typical flat box girder of the Great Belt Bridge in Denmark as the research object and employed such means as wind tunnel tests, finite element analysis, and harmonic superposition, combined with the actual wind environment and structural characteristics of the Great Belt Bridge, to simulate and analyze the influence of wind turbines on bridge buffeting response. Static three-component force coefficients of the bridge with wind turbines installed were measured in wind tunnel tests, and time-history response data of the bridge subjected to wind loads were generated depending on relevant data. Based on the quasi-steady assumption and Davenport buffeting force model, combined with the finite element model, the dynamic response of the bridge under different wind speeds was calculated and simulated. Six different wind turbine layout schemes were designed during the research process, considering variations in parameters such as the rotation axis height and layout spacing of wind turbines, to investigate the effects of different layout schemes on the lateral and vertical displacement and acceleration responses of the bridge. [Results] The results indicate that the installation of small horizontal-axis wind turbines increases the displacement and acceleration responses of the bridge to a certain extent. However, by selecting appropriate wind turbine layout schemes, it is possible to control vortex-induced vibration with a small effect on the structural safety and comfort of the bridge. The overall increase in lateral displacement of the bridge tends to decrease as the rotation axis height of the wind turbine blades decreases. For vertical response, the smallest increase in vertical displacement occurs when the wind turbine layout spacing is three times the beam height. Furthermore, by fitting the static wind loads caused by wind turbines on the bridge, this study proposed estimation formulas for drag and lift unit loads of bridges with wind turbines installed, which could effectively assess the impact of wind turbines on bridges under different layout schemes. [Conclusion] The impact of small horizontal-axis wind turbines on bridge dynamic response can be reduced through reasonable layout parameters (such as rotation axis height and layout spacing) without significantly affecting the structural safety and comfort of the bridge. The installation height and spacing of wind turbines have significant impacts on the dynamic response of the bridge, and reasonable layout schemes should be selected according to the specific conditions of the bridge to ensure its structural safety and comfort. This study proposed a mathematical model relating to the layout spacing and rotation axis height of wind turbines and wind load data of the bridge, providing theoretical support for optimizing control of wind-induced vibration of bridges by wind turbines in the future.

[Objective] Traditional cost prediction methods for power grid substation engineering often rely on single influencing factors or linear assumption models, which fail to comprehensively capture the complex non-linear relationships among multiple factors, resulting in low prediction accuracy. Furthermore, existing methods face challenges such as dimensionality explosion or information loss when handling high-dimensional categorical variables, and especially, overfitting is prone to occur in small-sample datasets. Therefore, this study aims to develop a robust cost prediction model for substation engineering that effectively integrates multi-source influencing factors, adapts to non-linear relationships, and performs well in small-sample scenarios, thereby providing more accurate technical support for investment decisions in power grid enterprises. [Methods] To address these issues, a substation engineering cost prediction model (ME-XGB) based on the fusion of mean encoding (ME) and the extreme gradient boosting (XGBoost) framework was proposed. First, 13 key influencing factors were extracted from dimensions such as equipment and materials, construction techniques, construction scale, geographical environment, and design standards, covering both categorical and continuous variables. For categorical variables exhibiting non-linear relationships with cost, ME was applied for feature engineering. This method converted categorical variables into continuous features by calculating the mean of the target variable (cost per unit capacity) within each category and combining with a smoothing factor to retain category information while avoiding dimensionality explosion. Second, the XGBoost algorithm was utilized to construct the prediction model. The generalization ability of the model was enhanced by integrating multiple decision trees to iteratively correct residuals and incorporating regularization terms and hyperparameter tuning. Experiments were conducted using 200 substation engineering samples from a power grid company, which were randomly divided into a training set (80％) and a test set (20％). The performance of ME-XGB was compared with MK-TESM based on a Mann-Kendall (MK) trend test method and a three exponential smoothing method (TESM), backpropagation (BP) neural network, and the original XGBoost model by using mean absolute error (M_AE) and goodness of fit (R²) as evaluation metrics. [Results] Experimental results demonstrate that the ME-XGB model significantly outperforms comparative models in prediction accuracy on the test set. Specifically, the median and mean M_AE values of ME-XGB are 5 and 6.875, where are lower than those of MK-TESM, BP neural network, and the original XGBoost. Additionally, the R² value of ME-XGB reaches 0.857 9, significantly higher than those of the other models, indicating stronger explanatory power for data variations. Boxplot analysis further reveals that ME-XGB has the narrowest distribution range of prediction errors, confirming its greater stability. Hyperparameter tuning results show that settings of hyperparameters such as tree depth and learning rate effectively balance model complexity and overfitting risks. [Conclusion] The proposed ME-XGB model addresses the challenges of non-linear representation and dimensionality control for categorical variables through ME, while leveraging the ensemble learning capability of XGBoost to significantly enhance prediction performance in small-sample scenarios. ME-XGB outperforms traditional models in terms of M_AE, R², and error stability, providing a more reliable cost prediction tool for power grid enterprises. Future research can further explore the modeling of dynamic influencing factors and extend the application of the model to cross-regional projects through transfer learning.

[Objective] With the continuous expansion of oil and gas pipeline transportation, the importance of pipeline safety inspection has become increasingly prominent. Stress concentration at pipeline defects is the main cause of crack propagation and fracture accidents. However, existing detection methods struggle to achieve quantitative stress evaluation. [Methods] This study proposed a pipeline stress detection method based on dual-field stress-magnetic coupling. By incorporating changes in the Jiles-Atherton (J-A) model parameters under different pipeline stress states, a magnetic stress detection model was built. The effects of elastic stress, plastic strain, and external magnetic fields on magnetization intensity and magnetic signal characteristics were systematically analyzed. The study was grounded in the principles of magnetic stress detection, the J-A model, and magnetic charge theory. By examining the influence of stress at different stages and external magnetic fields on magnetization intensity and magnetic signals, the relationship between hysteresis loops and magnetization intensity under varying conditions was established. In addition, the variation patterns of axial and radial signals under different stress and magnetic field conditions were identified. A proportional coefficient was introduced to develop a dual-magnetic field stress detection model, and separate models for elastic and plastic stress detection were built. Finally, experiments were conducted to verify the theory. Equivalent magnetic field strength formulas for the elastic stress and plastic strain stages were derived, clarifying the variation laws of the pinning coefficient k, shape coefficient a, and domain wall coupling coefficient α with stress. Experimental validation was conducted using X80 pipeline steel specimens subjected to tensile loads ranging from 10 to 80 kN and external magnetic fields from 0 to 10A/m, with magnetic signal characteristics measured. [Results] The axial component of magnetic signals under different magnetic fields and stress levels exhibits distinct peaks, with peak positions remaining stable despite variations in external fields or stress. Tangential peaks increase with the external magnetic field, aligning with theoretical calculations. Experimental data indicate that the model closely matches measured results under high stress, with minimal error, while low-stress scenarios show slight deviations due to parameter fitting limitations. [Conclusion] In the elastic stage, tensile stress causes the hysteresis loop to rotate counterclockwise initially and then clockwise. Magnetization changes significantly under weak magnetic fields, whereas stress effects become negligible under strong fields. During the plastic stage, plastic strain reduces the slope of the magnetization curve, and both the initial magnetization curve and hysteresis loop rotate clockwise. Magnetization intensity is proportional to magnetic signals, with the ratio of strong magnetic signals to magnetization intensity serving as a proportionality coefficient dependent solely on defect size. The dual-magnetic field stress detection model demonstrates high accuracy under high stress, confirming its capability for stress detection. This study innovatively integrates the dual-magnetic field method with J-A theory, proposing a proportional coefficient-based model for separating elastic and plastic stresses. The approach resolves the issue of overlapping defect and stress signals in traditional methods, providing a high-precision, quantifiable technical solution for stress detection at pipeline defects. This advancement holds significant value for preventing pipeline failures and ensuring safe energy transportation.

[Objective] With the increasing demands for flight safety of unmanned aerial vehicles (UAVs), the dynamic characteristics of landing gear systems have become a critical research focus in UAV design. This study focuses on the landing contact mechanical behavior of rubber footpads in six-link landing gears and investigates the problems of nonlinear mechanical characteristics in modeling. By constructing a precise dynamic contact model, this research aims to elucidate the mechanical response mechanisms of rubber buffers under impact loads and provide theoretical support for optimizing the structural design of cushioning systems at landing gear foot ends. [Methods] A nonlinear contact mechanics model for rubber materials was developed based on the theoretical framework of the continuous contact force method. Innovatively integrating Hertzian contact theory with the Mooney-Rivlin strain energy function, the model accurately characterized the hyperelastic characteristic of rubber materials and the dynamic coupling effects at contact interfaces through non-ideal elastic collision relationships. On the ABAQUS platform, a finite element model adopting the Mooney-Rivlin hyperelastic constitutive model was established, and the landing collision process was numerically simulated using an implicit dynamic solver. A drop impact test bench equipped with force sensors was constructed to obtain experimental data for model validation. This integrated methodology, combining theoretical modeling, numerical simulation, and experimental validation, effectively overcomes the limitations of traditional empirical formulas. [Results] Systematic analysis reveals the influence of multiple physical parameters on contact mechanical characteristics. When the drop height increases within the range of 50 mm to 200 mm, the peak contact force exhibits proportional growth, with an increment of 1.78 kN. Within the load mass range of 5 kg to 20 kg, the peak contact force demonstrates an approximately linear relationship with load mass, showing an increase of 1.02 kN. Notably, increasing footpad thickness has an insignificant effect on reduction in impact force, while optimizing the footpad shape can effectively mitigate impact-induced vibrations. Comparative studies on structural shapes demonstrate that conical footpads, compared to traditional cylindrical designs, exhibit more even force distribution and effectively mitigate impact-induced vibrations. Experimental validation confirms the effectiveness of the model, with the peak contact force error being merely 6％ and a phase shift of key parameters controlled within 3 ms under the condition of 100 mm drop height. [Conclusion] The contact force demonstrates approximately directly proportional relationships with both drop height and footpad thickness, though the effect of thickness is relatively weak. Footpad shape optimization significantly reduces impact-induced vibrations, with conical footpads exhibiting superior cushioning performance. This study achieves theoretical breakthroughs in two aspects. A dynamic contact prediction method for rubber buffers was proposed by combining the continuous contact force method with the hyperelastic constitutive model, resolving the technical bottleneck of traditional approaches in addressing nonlinear coupling effects. A quantitative evaluation framework for cushioning performance was established by investigating the influence of multiple physical parameters on contact force at landing gear foot ends, providing a reliable theoretical basis for foot-end parameter optimization.

[Objective] The optimization of electricity supply and demand matching and regulation in smart grids is becoming increasingly complex, and traditional static optimization methods cannot meet the optimization requirements of smart grids. To this end, a self-learning optimal control method was proposed to solve the optimal control problem of ice storage air conditioning (IAC) systems. [Methods] The adaptive dynamic programming-particle swarm optimization (ADP-PSO) algorithm was adopted to address the optimal control problem of the systems. A two-layer iterative adaptive dynamic programming method was designed to learn the optimal control strategy, where the inner iteration calculated the sequence of transformed iterative control laws, and the outer iteration optimized the iterative value function. Meanwhile, a parallel control scheme was developed to obtain the optimal control suitable for the IAC system, which could meet the cooling demand at the lowest operating cost. [Results] Simulation results and comparative studies verify the effectiveness of the proposed algorithm. [Conclusions] The proposed ADP-PSO algorithm can achieve optimal energy matching. This strategy can make the iterative value function converge to the optimum, thereby obtaining the optimal control strategy and minimizing the system operating cost.

[Objective] Interior permanent magnet (IPM) motors are widely adopted as submersible motors in oil well applications due to their structural stability, high efficiency, and superior power factor. However, the constrained wellbore diameter and elevated ambient temperatures in deep-well environments impose stringent requirements for enhanced torque density and anti-demagnetization capability of IPM motors. To address these challenges, a novel sine-shaped permanent magnet (PM), synthesized from flat and arched PM, was adopted in this study. The adopted PM optimizes rotor space utilization above conventional flat PM, thereby increasing permanent magnet volume and d-axis permanent magnet thickness, improving torque density and anti-demagnetization capability of IPM motors. [Methods] Maintaining constant dimensions of the flat PM, the finite element analysis (FEA) was employed to systematically evaluate the effects of arched PM sagitta on short-circuit current, anti-demagnetization capability, and no-load and on-load electromagnetic performance. Moreover, the equivalent ring method was implemented to quantify the maximum stress of the rotor core under various sagittas, ensuring the mechanical integrity of the optimized rotor structure. [Results] Although the short-circuit current of the IPM motor will increase as the sagitta increases, its permanent magnets exhibit stronger anti-demagnetization capability. While increasing the sagitta will increase the maximum stress of the rotor core, it is much lower than the yield stress of the core material, meeting practical needs sufficiently. Moreover, the effect of a smaller sagitta on the reluctance torque of the IPM motor can be ignored. When the sagitta is greater than 3 mm, the maximum reluctance torque decreases significantly as the sagitta increases, while the total output torque keeps increasing and torque ripple decreases. [Conclusion] Taking into account the overall influence of the sagitta on the motor′s performance, a suitable sine-shaped PM size was selected, and a prototype was manufactured and tested. The experimental results are in good agreement with the 2D FEA simulation results, verifying the accuracy of the simulation analysis, which provides a new approach for the rotor design of the IPM motors.

[Objective] Power engineering projects are typically characterized by high costs and long durations, and their construction processes are influenced by various factors such as climate conditions and material costs. Traditional methods for cost and duration prediction are mainly based on experience, which can lead to underestimated or excessive cost estimates, resulting in project delays or resource waste. With the rapid development of machine learning techniques, data-driven methods have been introduced in cost and duration prediction. However, due to the small size of datasets in power engineering, traditional machine learning models often suffer from overfitting, which limits their predictive performance. Thus, a hybrid model combining support vector regression (SVR), classification and regression trees (CART), multivariate linear regression (MLR), and grey wolf optimization (GWO) was proposed to improve prediction accuracy and generalization ability on small datasets by enhancing the update strategy and parameter search method. [Methods] The main approach of this paper was to combine machine learning models with an improved GWO (iGWO) algorithm to develop an efficient framework for predicting the cost and duration of power engineering projects. SVR, CART, and MLR models were used as baseline machine learning methods. GWO was employed to search for optimal parameters to prevent overfitting, with two improvements introduced: using chaotic sequences to initialize the wolf pack positions to ensure population diversity, and optimizing the update strategy of the grey wolves′ positions and enhancing the search ability by sharing information within the surrounding pack. [Results] Experimental results show that the proposed hybrid model outperforms traditional methods in cost and duration prediction. Performance comparisons on the training and testing sets indicate that traditional machine learning models are prone to overfitting, which results in poor generalization. In contrast, the model combined with GWO improves this issue. The MLR+GWO hybrid model performs better than the other models on both the training and testing sets. Further experimental results reveal that the convergence speed of the hybrid model is significantly accelerated by the iGWO algorithm. It reaches optimal fitness within 6 to 8 iterations, while the traditional GWO algorithm requires 11 to 12 iterations to achieve similar results. Additionally, the improved algorithm effectively avoids the issue that the traditional GWO algorithm is prone to falling into local optima. [Conclusion] The hybrid model based on linear regression and iGWO demonstrates performance advantages in predicting costs and durations of power engineering projects. The iGWO algorithm enhances the global search capability and convergence speed through optimized initialization sequences and update strategies. The proposed hybrid model exhibits better generalization performance, compared to traditional machine learning models. Compared with traditional methods, this approach performs better in terms of prediction accuracy and training efficiency.

[Objective] Conducting a state evaluation of secondary equipment in power systems is crucial for mitigating the operational risks of the power grid and improving grid reliability. To address the logical issues in the analytic hierarchy process (AHP) and the limitations of subjective judgment in the entropy weight method, this study proposed an improved entropy weight method for assessing the health status of secondary equipment. [Methods] Based on the fundamental characteristics of secondary equipment in the power system, both technical and management indicators for the state evaluation were developed. The study utilized forward, reverse, and trapezoidal mapping relationships to standardize the indicator parameters. In addition, a membership function based on normal distribution was adopted. This function retained valid information from high membership intervals, incorporating information from low membership ranges, and avoided misjudgment caused by an overemphasis on the low membership range. The weight principle of AHP was used to establish the judgment matrix of different evaluation indicators, and the coefficient of variation in the entropy weight method was introduced based on the arithmetic mean and standard deviation of each indicator, enabling an objective representation of the evaluation indicator weight. Subsequently, a comprehensive model for the state evaluation of secondary equipment was established. The model was validated using 36 protection devices in a substation. [Results] The verification results demonstrate that the evaluation results aligns with the actual operation status of the protection device. The membership value for “good” is 0.890 1, and for “fair” it is 0.097 9, which allows for the determination that the 220 kV main transformer protection device operates normally and consistents with the actual operational state of the protection device. The range of the membership function for evaluation indices obtained using AHP is 0.321 0, while the entropy weight method yields a range of 0.341 4, which may lead to misjudgments. Longitudinal comparisons of the AHP-entropy weight method and the entropy method′s weighting algorithms show that the membership degree ranges are 0.125 0 and 0.184 9, with minimum values of 0.806 5 and 0.708 8, respectively, with no misjudgments. In this method, the difference in the range values of the membership degree is 0.048 1, with maximum and minimum values of 0.900 0 and 0.851 9, resulting in a narrower fluctuation range and higher judgment reliability. [Conclusion] The innovation of this study lies in the combination of AHP and the entropy weight method, which effectively avoids the interference of human factors in subjective weighting. Moreover, by incorporating objective factors into equipment evaluation and introducing an entropy weight calculation method based on the coefficient of variation, the weight calculation accurately reflects the equipment′s actual operation status. The actual calculation results show that the proposed method more effectively reflects the actual state of equipment operation and provides crucial support for equipment operation and maintenance.

[Objective] With the continuous expansion of the power grid scale and the increasing complexity of its structure, traditional power grid modeling and visualization methods have gradually revealed many issues. For example, modeling accuracy often fails to meet the refined display requirements of complex grid structures. Application scenarios are limited and unable to effectively address diverse business needs. Moreover, there is a lack of scientific and effective verification mechanisms to ensure the accuracy and reliability of modeling results. To address these challenges, this study proposed a 3D power grid modeling and verification method integrating GIS-GIM and DETR networks, to achieve high-precision 3D grid modeling and establish an effective verification system, providing a solid data foundation and reliable decision support for grid planning, operation and maintenance, and management. [Methods] The first step involved integrating the grid information model (GIM) into the geographic information system (GIS). By leveraging GIS′s powerful geospatial analysis and display capabilities, and combining GIM′s detailed descriptions of grid equipment and topological structures, a more comprehensive 3D grid modeling approach was achieved, visually presenting the grid′s overall layout and equipment distribution from a geospatial perspective. Second, the DETR network was improved by optimizing its structure, adjusting parameter settings, and employing more effective training strategies, enabling it to more accurately detect and classify 3D grid equipment. During training, a large volume of 3D grid equipment data was collected to build a rich and diverse dataset. The data were then annotated and preprocessed to improve the model′s generalization ability. Last, the improved DETR network was applied to the 3D grid modeling process to detect and classify equipment in the modeling results individually, ensuring the accuracy of equipment information and the overall accuracy of the modeling results. [Results] To validate the effectiveness of the proposed method, experimental analyses were conducted on 100 sets of equipment data from three newly built substations. The results show that, compared to traditional modeling methods, the proposed 3D grid modeling method that integrates GIS-GIM and DETR networks significantly improves modeling accuracy, enabling more precise restoration of the spatial positions, structural forms of grid equipment, and connection relationships between equipment. Regarding the verification of the modeling results, the verification network demonstrates a good performance with an accuracy rate of 93.14％, indicating that the method can effectively detect potential errors and deviations in the modeling process and ensure the reliability of modeling results. [Conclusion] The proposed 3D power grid modeling and verification method, integrating GIS-GIM and DETR networks, performs excellently in improving grid modeling accuracy and establishing an effective verification mechanism, meeting the high-precision requirements of actual grid modeling. The method contributes significantly to improving the scientific basis for grid planning and provides intuitive 3D visualization for daily operations, maintenance, fault diagnosis, and repair, supporting reliable decision-making in grid management. It holds important theoretical significance and broad application prospects.

[Objective] Agricultural parks, characterized by abundant renewable energy resources, play a pivotal role in advancing green and low-carbon transformation under the carbon peaking and carbon neutrality goals. However, current agricultural parks face challenges such as low energy utilization efficiency, imbalanced multi-energy distribution, and insufficient local renewable energy accommodation capacity, which hinder agricultural productivity and sustainable development. To address these issues, this study proposed a deep learning-based optimization method for constructing a more economical and low-carbon integrated energy system (IES) in agricultural parks. [Methods] First, a multi-objective optimal scheduling model for agricultural park IES was established, integrating economic objectives such as fuel costs of gas turbines, grid interaction costs, and equipment maintenance costs, while formulating mathematical constraints for multi-energy coupling systems. Second, an improved long short-term memory (LSTM) neural network was employed to predict photovoltaic/wind power outputs and load demands. The hyperparameters of the LSTM model, including hidden layer units and learning rates, were dynamically optimized using quantum particle swarm optimization (QPSO) to enhance prediction accuracy. Finally, to mitigate premature convergence in the traditional golden sine algorithm (GSA), an enhanced GSA algorithm was proposed by incorporating Lévy flight strategies to expand the search space and designing dynamic weight mechanisms to balance global exploration and local exploitation capabilities. [Results] Case studies demonstrate that the errors of improved QPSO-LSTM prediction model are controlled within 5％, outperforming traditional optimization algorithms in accuracy and robustness against local optima. For scheduling optimization, the enhanced GSA algorithm achieves a 69.7％ reduction in daily operational costs and a 27.9％ improvement in local renewable energy accommodation rates compared to unscheduled scenarios, significantly surpassing conventional GSA and other methods. These results validate the algorithm′s effectiveness in balancing economic efficiency and low-carbon requirements for multi-energy coordination. [Conclusion] The proposed deep learning-based optimization framework enables high-precision power prediction and cost-effective scheduling for agricultural park IES. It significantly reduces operational costs while enhancing renewable energy utilization, demonstrating superior performance in synergizing economic and low-carbon objectives. This study provides a reliable technical pathway for the efficient and sustainable operation of agricultural park IES.

[Objective] Industrial control protocol parsing is a critical component of industrial internet security. However, traditional methods suffer from poor universality and low accuracy. These issues lead to a low efficiency in protocol parsing, making it difficult to meet the demands for high precision and adaptability in real-world industrial scenarios. [Methods] A deep learning-based reverse engineering method was proposed for industrial control protocols by integrating a bidirectional encoder representations from transformers (BERT) pre-trained model, a bidirectional long short-term memory (BiLSTM) network, and conditional random fields (CRF). The goal is to enhance the universality and accuracy of protocol parsing, thereby providing technical support for security analysis and vulnerability mining in industrial control systems. First, the BERT pre-trained model was employed to dynamically encode industrial control protocol data into high-dimensional word vector representations, so as to capture the semantic information of the protocol data. Leveraging the powerful contextual understanding capabilities of BERT, the model effectively handled the complexity and diversity of protocol data. Subsequently, a BiLSTM network was utilized to model the relationships between protocol data as well as between protocol data and label data. The BiLSTM network captured long-range dependencies within the protocol data, enabling a better understanding of the structure and semantics of the protocol. Finally, CRF were introduced as constraints to optimize the prediction of protocol formats and semantics. By incorporating transition probabilities between labels, CRF further enhanced prediction accuracy and consistency. The combination of the BERT pre-trained model, BiLSTM network, and CRF enabled the format extraction and semantic analysis of industrial control protocols. Additionally, the proposed method was optimized for large-scale protocol data, which ensured efficiency and stability in complex industrial scenarios. [Results] Experiments were conducted on three typical industrial control protocols. The results demonstrate that the proposed method achieves an accuracy of over 96％ in both format extraction and semantic analysis, outperforming traditional methods. The method exhibits high adaptability and accuracy across different protocols, effectively identifying field boundaries and semantic information. [Conclusion] The proposed method significantly improves the universality and accuracy of industrial control protocol parsing, providing reliable technical support for security analysis in industrial control systems. Future work will focus on further optimizing the model, expanding its application scenarios, and enhancing its practicality.

[Objective] Power engineering projects have long construction cycles and are affected by various uncertainties, which may lead to significant cost increase. Therefore, accurately estimating contingency costs is crucial for project management. However, traditional experience-based methods have large errors and are difficult to adapt to complex engineering environments. Existing methods based on fuzzy expert systems and machine learning have improved performance but still face challenges such as parameter optimization difficulties and severe overfitting. To address these issues, a new contingency cost estimation method was proposed. It leverages the advantages of adaptive network-based fuzzy inference system (ANFIS) in handling uncertainty problems and introduces a principal component analysis (PCA) module to mitigate overfitting and improve prediction accuracy. [Methods] A contingency cost estimation method integrating risk analysis and ANFIS was proposed. First, the relationship between contingency costs and 13 key risk factors affecting power engineering costs was modeled. Then, ANFIS was introduced to utilize fuzzy logic for handling uncertainty problems. ANFIS processed input variables through fuzzification and leveraged neural networks for inference, avoiding the dependency on fuzzy rule sets in traditional fuzzy expert systems. To further enhance prediction accuracy, a PCA module was incorporated into ANFIS, which eliminated redundant information through dimensionality reduction and alleviated overfitting issues associated with small datasets. [Results] In the experiments, 210 power engineering contingency cost data samples were selected, with 80% randomly assigned to the training set and 20% to the test set. The performance of four methods was compared:a Mamdani fuzzy inference based method, a support vector machine (SVM) based method, an ANFIS based method, and an improved ANFIS based method. The experimental results indicate that while the ANFIS based method outperforms the existing two methods on the training set, it suffers from severe overfitting on the test set. After incorporating the PCA module, the improved ANFIS based method achieves significantly better test performance, demonstrating stronger generalization ability and faster convergence. [Conclusion] The proposed contingency cost estimation method based on the improved ANFIS combines the advantages of fuzzy inference and neural networks, enhancing prediction accuracy for power engineering contingency costs. The key innovations of this study are as follows. A contingency cost estimation method was proposed, effectively addressing the uncertainty problem by combining the advantages of fuzzy logic and neural networks. In addition, a PCA module is introduced into ANFIS, which reduces redundant information through dimensionality reduction, effectively avoids model overfitting, and improves generalization capability. The proposed method provides an intelligent solution for power engineering budget management and can be extended to other fields involving uncertainty cost estimation.

[Objective] With the rapid development of power generation from renewable energy, photovoltaic power generation is widely adopted due to its merits of safety, reliability, flexible adjustment, and clean production. Due to the real demand for large-scale photovoltaic power generation, multiple inverters connected in parallel and grid-connected inverters are often adopted in photovoltaic power stations to enhance the power generation efficiency. However, with the expansion of the grid-connected scale, the inductive impedance under the weak grid poses a threat to the stability and reliability of the grid, leading to poor global resonance suppression as well as a high risk of uncontrollable system stability. The aim of this study is to propose a global resonance suppression strategy for photovoltaic (PV) multi-inverter parallel system to guarantee the stable operation of the system and improve its power quality. [Methods] Firstly, a Norton equivalent model of the PV multi-inverter parallel system was constructed. Based on this model, this paper analyzed in depth the resonance characteristics of the multi-inverter parallel system under a weak grid, and it was found that the coupling resonance frequency was negatively correlated with the number of inverters. Secondly, based on the control theory, the optimal control strategy combining capacitor current feedback and grid voltage feed-forward was applied to solve the global coupling resonance problem in the multi-inverter system. At the same time, the global resonance suppression strategy of paralleling virtual admittance at the point of common coupling (PCC) was designed to realize the effective suppression of global resonance from the system level. Finally, comparative simulation experiments before and after adopting the strategy proposed in this paper were conducted under two-inverter parallel system and four-inverter parallel system. In addition, simulation experiments were also carried out to compare the suppression effect under the same system by using other methods reported previously and the strategy proposed in this paper. The correctness and effectiveness of the proposed strategy were verified through simulation. [Results] Theoretical analysis and simulation results show that the proposed global resonance suppression strategy can significantly improve the stability of the system. The rationality of the control strategy and its parameters are validated and optimized by the Nyquist criterion. Simulation test results show that after the application of the proposed strategy, the harmonic content in the system is reduced from 17.32％ to 1.71％. This indicates that the proposed strategy can effectively suppress the global resonance of the system and enhance the stability of the system operation. [Conclusion] In this paper, a Norton equivalent model of PV multi-inverter parallel system was constructed. Innovatively, the resonance characteristics of the multi-inverter parallel system under a weak grid were analyzed, and a global resonance suppression strategy of paralleling virtual admittance at the PCC was proposed on the basis of the optimal control of capacitor current feedback and grid voltage feed-forward. The strategy effectively improves the stability of the system operation in the presence of a large number of parallel inverters and high inductive reactance of the grid. The comparative simulation verification further demonstrates that the proposed strategy can suppress the global resonance of the system effectively, providing important reference for the efficient operation of PV power generation grid-connected system.

[Objective] In recent years, the development of lithium-ion batteries have encountered bottlenecks such as slow energy density improvement, high cost and narrow temperature adaptation range. Potassium-ion batteries featuring low cost and high energy density have become the ideal choice for the next generation of large-scale electrochemical energy storage systems. Phosphate fluoride (KVPO₄F) serves as the first-choice cathode material for potassium-ion batteries due to its solid three-dimensional framework and high operating voltage. However, the repeated embedding/removal of large potassium ions in the charge and discharge process will cause structural pulverization to KVPO₄F, resulting in rapid capacity decay and poor cyclical stability. Moreover, the structure formed by the covalent bond of the coordination polyhedron restricts the electron transfer mode, greatly hindering the dynamics performance of KVPO₄F cathode material, and resulting in poor magnification behavior and low actual capacity. The modification of KVPO₄F material is usually studied by such strategies as element doping, carbon coating, and morphology engineering to improve the capacity, magnification and cyclical stability of KVPO₄F cathode material, and thus enhance the potassium storage performance. However, due to the imbalance between lattice spacing, crystal face exposure and V³⁺ content, the capacity, magnification, and cyclical stability are difficult to be improved simultaneously. The synthesis of KVPO₄F cathode material usually consists of two successive heat treatment steps, including the preparation of the VPO₄ precursor and the secondary calcination of VPO₄ mixed with KF to produce KVPO₄F. Therefore, the crystal structure of VPO₄ is bound to affect the particle size and crystal face orientation of KVPO₄F, thus affecting the potassium storage stability of KVPO₄F. [Methods] A series of VPO₄ materials were prepared by the sol-gel and high-temperature annealing method, and the effects of different VPO₄ materials on the lattice and electrochemical properties of the final product KVPO₄F were studied. [Results] The results show that VPO₄ prepared at different temperatures can significantly affect the lattice exposure intensity, lattice spacing and V³⁺ content of KVPO₄F. As the temperature rises from 700℃ to 800℃, the lattice exposure intensity, lattice spacing and V³⁺ content increase first and then decrease. When VPO₄ annealed at 750℃ is employed as the precursor, the prepared KVPO₄F has the most intense lattice plane exposure, the largest lattice spacing and the highest V³⁺ content, which ensures excellent structural stability, ion migration and ion storage quantity during the charge and discharge process. The electrochemical property test shows that after 30 cycles at 0.2 C (1 C=131 mA/g), the specific capacity of KVPO₄F is 57.3 mAh/g, much higher than that of the control sample under the same conditions. Additionally, the reversible specific capacity of KVPO₄F at 0.2 C, 0.5 C, 1 C, and 2 C is 62.1, 53.8, 44.6, and 30.6mAh/g, respectively. [Conclusion] Based on VPO₄ regulation, this study determines the effect of precursor VPO₄ on the microstructure of the final product KVPO₄F, and reveals the internal mechanism of improving electrochemical properties, laying a sound foundation for obtaining high-capacity KVPO₄F cathode material.

[Objective] 6061 aluminum alloy is widely used because of its good comprehensive properties. However, the quality of its welded joints generally has certain limitations. This study aims to effectively improve the quality of 6061 aluminum alloy welded joints by using the method of laser shock peening, deeply explore the changes of mechanical properties and microstructure of welded joints before and after laser shock peening, and analyze the internal influence mechanisms, so as to provide a solid theoretical basis and practical guidance for the optimization of aluminum alloy welding process. [Methods] A 6061 aluminum alloy welded joint was selected as the research object, and its surface was treated by laser shock peening technology. In the process of treatment, the parameters of laser frequency, shock range, pulse width, and overlap rate of laser pulses were strictly controlled. The influence of laser energy on 6061 aluminum alloy welded joints was studied. The mechanical properties of welded joints before and after laser shock peening were analyzed, such as tensile strength and hardness. At the same time, the changes of microstructure characteristics such as grain size and shock layer thickness at the weld were observed and compared by means of microstructure analysis technologies, including optical microscopy, scanning electron microscopy, and electron backscatter diffraction (EBSD). [Results] First of all, in terms of the relationship between laser energy and tensile strength of welded joints, there is a clear positive correlation. Specifically, with the gradual increase in laser energy, the tensile strength of welded joints also increases steadily. Secondly, the detection of the hardness of the weld surface shows that the hardness is significantly improved after laser shock peening, and the increase is about 23％. Finally, from the microstructure point of view, the thickness of the laser shock layer changes significantly, greatly increasing from the initial 15.83μm to 30.77μm, which indicates that the laser shock has a deep impact on the surface of the material. At the same time, the grain size of the weld center also changes significantly, decreasing from the original 33.68 μm to 14.5 μm. The grains obviously become finer, namely that the microstructure is optimized. [Conclusion] Based on the above research results, it can be concluded that laser shock peening technology shows excellent effect in the treatment of 6061 aluminum alloy welded joints. The high energy generated on the surface of metal materials can effectively reduce the adverse effects of plastic deformation on the surface and interior of materials and promote grain refinement, which is the key factor to improve the mechanical properties of welded joints. Through laser shock peening, the tensile strength and hardness of welded joints are effectively improved, which not only helps to improve the reliability and durability of 6061 aluminum alloy welded structures in practical applications but also provides strong technical support for further expanding the application range of aluminum alloys in high-end manufacturing. In the future, the optimal process parameter combination of laser shock peening can be further studied in order to improve the quality of 6061 aluminum alloy welded joints more accurately and efficiently and promote the continuous development and innovation of aluminum alloy welding technology.

[Objective] Martensitic stainless steel (0Cr13Ni5Mo) has good forging, casting, and corrosion resistance performance and is therefore widely used in hydropower, chemical industry, and high-pressure vessels. However, the special working environment can accelerate failure of the 0Cr13Ni5Mo material, especially for hydraulic flow passage components which are subjected to sand impact and corrosion due to the complex water body. Therefore, it is necessary to take certain protective measures to improve the surface properties of the 0Cr13Ni5Mo material and thereby delay its failure. [Methods] To enhance the service life of the flow passage components, iron-based alloy coatings with different Nb content (0％, 5％, 7％, and 9％) were prepared on the surface of the 0Cr13Ni5Mo substrate by laser cladding technology. X ray diffraction (XRD), scanning electron microscopy (SEM), a Vickers hardness tester, and an electrochemical workstation were used to investigate the effects of Nb addition on the microstructure, phase composition, microhardness, and electrochemical properties of the iron-based alloy coatings. [Results] The results show that the microstructure consists of grey matrix, massive and petal-like VC reinforced phases, and reticulated Cr carbides. With the increase in Nb content, the size of massive and granular Nb carbides in the matrix increases gradually, and the carbide morphology changes from massive and granular to petal-like and butterfly-like, and the reticulated Cr carbides decrease gradually. The phase composition analysis shows that the four coating samples prepared by laser cladding are composed of martensitic phase with BCC structure, austenitic phase with FCC structure, carbide reinforced phase VC, and Cr₂₃C₆ phase. With the increase in Nb content, the peaks of NbC phase appear in the XRD curves of S2, S3, and S4 samples, indicating that the carbide reinforced phase NbC is generated by the in-situ reaction of Nb during the laser cladding process, and the austenitic phase in the matrix increases gradually. The microhardness of all samples increases with the addition of Nb, with the S3 sample exhibiting the highest microhardness of 645 HV. In electrochemical tests, the self-corrosion potential of the samples gradually increases with the increase in Nb content, and the self-corrosion current gradually decreases. Samples S3 and S4 show typical anodic polarization characteristics, including the active dissolution zone, the passivation zone, and the over-passivation zone which is formed after the rupture of the passivation film. Sample S4 has a large amount of carbides, which causes micro-electro-coupling corrosion, leading to a decrease in corrosion resistance. Sample S3 has the best electrochemical performance with a self-corrosion potential of -179.3 mV, and the self-corrosion current density is only 10.3％ of that of sample S1 and reaches 9.258×10^-8 A/cm². Its improved corrosion resistance is due to the Cr reduction in the MC-type carbides, which results in the dissolution of more Cr into the matrix phase and thereby an increase in the Cr content in the matrix phase. [Conclusion] In this study, a Nb-containing iron-based alloy coating of 0Cr13Ni5Mo material for hydraulic flow passage components was designed and prepared to promote the development of laser cladding technology for surface-strengthened coatings of flow passage components to a certain extent.

[Objective] With the continuous expansion of network scale and the evolving complexity of attack techniques, network traffic anomaly detection has become a critical link in ensuring network security and maintaining the stable operation of key information infrastructure. However, traditional machine learning methods generally face bottlenecks such as slow convergence and insufficient feature representation accuracy when handling complex network traffic feature extraction, which limits their effectiveness in practical anomaly detection scenarios. To address these challenges, an innovative spatiotemporal fusion deep learning model, C²-GRU, was proposed in this paper, which was based on a convolutional neural network (CNN)-enhanced learner with a gated recurrent unit (GRU). The proposed model aims to enhance the multi-dimensional detection performance for abnormal traffic. [Methods] A dual-fusion deep learning framework was designed, leveraging the strength of CNN in spatial feature extraction and the capability of GRU in temporal feature modeling. A C-GRU model was constructed to achieve preliminary spatiotemporal feature fusion. It was then cascaded with CNN to form the C²-GRU model, which extracted spatiotemporal features through dual parallel convolution operations. This approach effectively captured the multidimensional features of abnormal traffic in complex network environments. [Results] The experimental results demonstrate that the proposed model achieves optimal overall performance on the KDD99 dataset. Specifically, the fused model attains an accuracy of 99.89％ and an area under curve (AUC) of 0.990 2, significantly outperforming individual CNN and GRU models. Furthermore, compared to traditional anomaly detection models, the proposed model not only achieves high recognition performance but also exhibits a relatively short model runtime, which highlights its superior engineering applicability. [Conclusion] The proposed C²-GRU hybrid model, employing a dual-convolution fusion strategy, effectively enhances spatiotemporal feature learning, suitable for abnormal traffic detection in complex network environments. It has dual advantages in anomaly recognition accuracy and computational efficiency, capable of offering technical support for securing key information infrastructure and mitigating the economic losses caused by network attacks. The model is of significant practical reference value for ensuring network information security.

[Objective] Due to the influence of the limited regulated direct current (DC) power supply, amplitude control of each variable of the chaotic system, that is, variable compression, has become an essential prerequisite for chaotic circuit design and implementation. Currently, geometric control of the attractors of chaotic systems, such as amplitude control and bias control, is a hot research direction in the field of chaotic systems. Based on existing methods, a new amplitude control method was proposed in this paper in the expectation of exploring more potential applications of chaotic systems. [Methods] A five-dimensional chaotic system was developed, and its chaos was verified by using a three-dimensional phase diagram and Lyapunov exponents. After the absolute values of state variable-u in the two equations of the system were taken, two new switched chaotic systems were obtained. Compared with the phase diagram of the chaotic system, the amplitudes of these two new systems changed, and their shapes were highly similar, namely that global amplitude control was achieved. After the absolute value of-u in the second equation was taken, it became a memristive chaotic system. The existence of the memristor was verified by the pinched hysteresis loops of three frequencies. Further analysis of the memristive chaotic system was carried out. By adding the parameter k to the three nonlinear terms of the memristive chaotic system, it was found that the average amplitudes of the attractor on five dimensions changed accordingly, which indicated that the memristive chaotic system had a global amplitude control parameter. The existence of multi-stability in the memristive chaotic system was verified by the Lyapunov exponent spectrum changed with the memristive parameter a. Moreover, the absolute mean value of the signal and the phase diagram changed with a proved that when an appropriate value of the memristive parameter a was selected, global amplitude control could also be achieved. [Results] The simulation circuit equations, equivalent circuit diagram of the memristive chaotic system, and the simulated phase diagram of the chaotic system on the oscilloscope are highly similar to the computer simulation results, which indicates that the chaotic circuit design is of reliability. [Conclusion] The proposed five-dimensional chaotic system has strong chaotic property. The switching system with switching amplitude variation was proposed, providing a new direction for the research of memristive chaotic systems. In future work, it is possible to attempt to use a curved surface as the switching surface. Additionally, through computer simulation experiments, whether the phenomenon of switching amplitude variation widely exists in memristive chaotic systems will be further studied, and further work will be carried out to explore the principle of its existence. The phase diagram on the oscilloscope is highly consistent with the computer simulation experiment in five dimensions. The system has the characteristics of high dimensionality, strong chaos, and switching amplitude control, which make it have good application prospects in engineering.

[Objective] In the context of the rapid development of the aviation industry, the scale and level of air transportation have significantly improved, air transportation becomes an indispensable mode of transportation in economic activities. However, the issue of cargo loading path planning in air transportation limits the optimization of transportation efficiency and cost. To address the challenges of enhancing operational efficiency and optimizing costs in air transportation, this paper proposed an air transportation loading path optimization algorithm based on an adaptive genetic algorithm. [Methods] To elucidate the loading path optimization algorithm for air transportation, this study analyzed the actual needs of air transportation loading and the computational conditions of the path planning platform and explored the transportation cost factors influencing the optimization of air transportation loading paths. On this basis, an improved genetic algorithm with adaptive capabilities was employed, utilizing adaptive fitness functions, crossover probabilities, and mutation probabilities to circumvent the issues of poor stability and slow convergence speeds inherent in traditional algorithms. The essence of this algorithm was the dynamic adjustment of crossover probabilities and mutation probabilities to align with the evolutionary state of the population, thereby augmenting the algorithm′s global search capability and convergence speed. During the research, the encoding method of the adaptive genetic algorithm, the establishment of the fitness function, and the calculation method and control principle of crossover probabilities and mutation probabilities were detailed, along with the specific execution steps of the loading path optimization algorithm. The algorithm was implemented on the MATLAB platform and tested using actual distribution data from an air transportation airport. [Results] The simulation results demonstrate that compared to traditional genetic algorithm, intelligent water drop algorithm, and improved ant colony algorithm, the air loading path optimization algorithm based on the adaptive genetic algorithm exhibits significant advantages in both transportation efficiency and overall transportation cost. In other words, the air loading path optimization algorithm can effectively reduce the average transportation cost and enhance transportation efficiency. However, actual air transportation loading processes are influenced by complex environment factors, such as the size limitation of aircraft cargo hold and the complex road conditions during delivery. These problems have not been deeply considered in the algorithm, which indicates that there is still room for improvement in the algorithm. [Conclusion] In summary, the air transportation loading path planning algorithm based on adaptive genetic algorithm introduces an improved genetic algorithm with adaptive mechanism, which shows better global search ability and convergence speed in solving the air transportation loading path planning problem. This paper provides a new idea for air transportation loading path planning and is also of important theoretical and practical value for the field of air logistics. Future studies will aim to take into account more actual operating environment factors to further optimize algorithm performance.

[Objective] The iron and steel industry, as one of the pillar industries of economic development in China, has an irreplaceable position in the entire manufacturing industry. Hot rolled strip steel has the advantages of strong covering capacity, easy processing, and material saving and is the raw material for producing other steel products. Improving the surface quality of strip steel products is an important part of improving the quality of steel products. Due to the influence of many factors of production, processing, shooting, etc., the brightness of the surface defect image of the original strip steel is uneven, and the contrast between the defect area and the non-defect area is low. As a result, the defect information is not clear enough for easy detection. To solve the above problems, a method for surface defect image enhancement of strip steel based on wavelet denoising and improved homomorphic filtering was proposed. [Methods] The original image was decomposed into low-frequency component and high-frequency component by two-level wavelet transform. The low-frequency component contained the main information of the original image, which was enhanced to improve the overall effect of the image. The improved homomorphic filtering algorithm and the contrast limited adaptive histogram equalization (CLAHE) algorithm were used to enhance the low-frequency component, equalizing the image brightness and improving the overall contrast. Moreover, the low-frequency images after being processed by the above two algorithms were fused with appropriate weights to obtain the enhanced low-frequency component. The high-frequency component contained the detail information of the image and noise. The improved threshold function was used to improve the denoising effect of the high-frequency component, and the edge details were well preserved. Finally, the processed low-frequency and high-frequency components were subjected to wavelet reconstruction to obtain the final enhanced image. [Results] Multiple sets of comparative analysis were conducted on the processing results of the algorithm through subjective visual evaluation and objective evaluation indicators. Brightness is significantly improved for all kinds of surface defect images of strip steel which are enhanced by the proposed algorithm compared with other algorithms, and the overall brightness remains balanced. At the same time, the contrast is improved, and the texture details and defect information of the images are more obvious. The mean square error (MSE), peak signal-to-noise ratio (PSNR), and image entropy (IE) were used for evaluating the algorithms, and each parameter was comprehensively analyzed. The proposed algorithm has a remarkable effect on improving contrast and reducing noise. It retains more details and leads to less distortion. [Conclusion] Experimental results show that the proposed algorithm can effectively enhance the brightness evenness and overall contrast of surface defect images of strip steel, strengthen the denoising effect, and significantly enhance defect information and edge details. It is suitable for the detection of various types of strip steel surface defects.

[Objective] The cost of distribution network engineering is influenced by multidimensional factors such as scale and capacity, equipment and material costs, and geographical conditions. Traditional statistical methods (e.g., linear regression) struggle to handle high-dimensional nonlinear data effectively, while existing machine learning approaches, despite incorporating feature reduction techniques, still exhibit limitations. For instance, principal component analysis (PCA) sacrifices prediction accuracy for dimensionality reduction, and grey relational analysis (GRA) ignores feature interactions. Therefore, there is an urgent need for a prediction method that retains critical feature information while accounting for complex inter-feature relationships. This study integrated recursive feature elimination (RFE) with the random forest (RF) algorithm to develop a RFE-RF prediction model, aiming to resolve feature redundancy and nonlinear modeling challenges. [Methods] A technical framework of “feature selection-model construction-experimental validation” was adopted. For feature selection, the recursive feature elimination (RFE) method was employed, which iterated training models to gradually eliminate features with minimal predictive contributions, retaining an optimal feature subset. For model construction, the RF algorithm was utilized. Based on ensemble learning principles, RF constructed multiple decision trees and averaged their outputs, effectively mitigating overfitting and enhancing model robustness. RF was insensitive to noisy data and quantified feature importance, providing reliable feature ranking criteria for RFE. By embedding RFE into the RF training process, a closed-loop optimization workflow was established. [Results] Experimental validation used data from 190 distribution network engineering projects provided by a power grid company, covering 21 initial features such as voltage level, line length, and equipment costs. Categorical features were numerically encoded while preserving their original distribution characteristics. Through five-fold cross-validation and root mean square error (RMSE) optimization, the optimal feature subset was identified as 12 optimal feature subsets, including such key factors as line length, comprehensive cable price, and voltage level. Compared with traditional linear regression (LR), RF, and mutual information-based RF (MI-RF) algorithms, the RFE-RF algorithm achieves a mean absolute error (MAE) of 8.6579 and a mean absolute percentage error (MAPE) of 6.97％ on the test set, significantly outperforming other algorithms. The MAE of RFE-RF on the test set increases by only about 4.5％ compared to the training set, indicating lower overfitting risks and demonstrating that feature selection effectively enhances model stability. [Conclusion] Feature selection is pivotal for improving the accuracy of distribution network cost prediction. RFE dynamically eliminates redundant features through iterative processes, substantially reducing data dimensionality and noise interference. The RFE-RF model combines high precision with strong interpretability, reduces MAE significantly compared to traditional models, and clearly quantifies the impact weights of individual features on costs. This study marks the application of combining RFE and RF in cost prediction for distribution network engineering, addressing challenges in feature interaction and redundancy filtering and providing a new paradigm for data modeling in complex engineering systems. The model serves as a precise cost prediction tool for power grid enterprises, aiding investment decisions and cost control, thus advancing intelligent and refined construction of distribution networks. Moreover, it reveals the impact mechanism of feature selection on the generalization capability of machine learning models, offering practical references for feature optimization in high-dimensional nonlinear datasets.

[Objective] Due to the long-term exposure of overhead transmission lines to the natural environment and the significant impact of environmental factors, timely monitoring of their operating status plays a key role in the safe operation of the power grid. With the development of UAV flight control technology and the widespread use of detection technologies such as infrared, ultraviolet, and LiDAR, these methods are increasingly used in the inspection of power transmission lines. However, traditional methods currently only show optimal results in single-scenario line inspection. In more complex environments, such as mixed transmission line inspections, it is challenging to quickly and accurately analyze transmission line inspection data. Therefore, this study proposed an optimization method for point cloud data processing in hybrid transmission line inspection. [Methods] First, a transmission line inspection point cloud data processing platform was constructed. LiDAR mounted on the UAV platform collected the mixed point cloud data of the transmission line and processed it in four stages: data management, preprocessing, classification, and intelligent inspection. The mixed point cloud data were thinned using the octree method to reduce redundant data and ensure the accuracy and quality of the data. Finally, a neural network model was designed to optimize the sparse data, consisting of three main parts: the feature learning layer, the convolutional layer, and the classification layer. The feature learning layer avoided the impact of the disorder in 3D point cloud data on feature extraction through multiple projections and maximum pooling. The convolutional layer extracted common features from voxel grids and surrounding entities while incorporating traditional transmission line feature extraction algorithms to extract voxel grid features. The classification layer included a fully connected layer with a ReLU activation function, using the Softmax model as the classification function to obtain the classification results of the mixed point cloud data. [Results] In the experiment, the LDLRS3100 LiDAR was selected to collect point cloud data of a transmission line channel in a certain area. The UAV LiDAR system has a range of 360 m, a flight speed of 20 km/h, and a flight altitude of 150 m. The proposed method was analyzed based on the Pytorch platform, and the results show that it can effectively identify the differences between transmission lines and ground objects, and obtain clear information on the tower and its surrounding environment. The overall accuracy reaches 92.71％, which is significantly better than other comparative methods. To balance the highest sparsity rate and the best visual effect of the point cloud data, the sparsity density is set to 0.02 m. [Conclusion] By optimizing the point cloud data of mixed transmission line inspections using the octree sparsity method and a neural network model, various types of point cloud data can be quickly and accurately classified, thus improving the reliability of intelligent transmission line inspections.

[Objective] The influence of photovoltaics (PV)-assisted current and extraction current on conventional relay protection hinders the effective functioning of relay protection equipment. A multi-objective setting method for relay protection in distribution networks suitable for conditions with high permeability of distributed PV was proposed to address this problem, which is aimed at enhancing the rapidity, sensitivity, and selectivity of protection, and ensuring economic viability and practicality, thus effectively safeguarding the power grid security and supporting the widespread access of distributed PV. [Methods] The influence of PV-assisted current and extraction current on the protection configuration of the distribution networks was analyzed, and the problem of unwanted operation and refuse operation of distribution network protection caused by PV access was avoided by introducing distance protection and instantaneous current protection as the protection criteria. A multi-objective optimization model with the optimal parameters of protection rapidity, sensitivity and selectivity was built, and the particle swarm optimization (PSO) algorithm was improved by adopting the dynamic splitting operator to make the solution of the protection setting meet the practical application requirements. [Results] High-permeability distributed PV results in unwanted operation or refuse operation of distribution network protection, which is effectively avoided by introducing distance protection and instantaneous current protection as the protection criteria. The multi-objective optimization protection configuration model was built, and the evaluation indexes of the overall protection effect of a certain area were formed, with the solution of the protection setting completed based on PSO algorithm. Finally, the overall evaluation of the protection effect under high-permeability PV access was realized, with the rapidity, sensitivity, and selectivity of protection improved. [Conclusions] The results show that the combination of distance protection and instantaneous current protection can effectively avoid the influence of the PV-assisted effect on the conventional instantaneous current protection. The protection performance can be effectively improved by the proposed multi-objective optimization scheme. Under the equilibrium strategy, the rapidity, sensitivity, and selectivity increase by about 82.2％, about 3.8％, and about 33.1％, respectively. The innovation of this study is that the combination of distance protection and instantaneous current protection was adopted to form the protection criteria, thus avoiding the problem of unwanted operation and refuse operation of the distribution network protection due to PV access. Additionally, a multi-objective optimization scheme for protection settings was constructed, and PSO algorithm was improved by employing the dynamic splitting operator, thereby avoiding the limitations of PSO algorithm and improving the reliability and applicability of protection settings.

[Objective] With the rapid development of power engineering, construction site safety has become increasingly critical. Traditional manual inspection methods are time-consuming and prone to errors. In recent years, advancements in computer vision, deep learning, and knowledge graph technologies have made it possible to automatically recognize unsafe operation behaviors. However, existing computer vision methods have limitations in detecting small objects and lack high-quality databases for unsafe operation inference. To address these issues, knowledge graphs, ontology models, graph databases, and computer vision techniques were integrated to detect unsafe operations through entity detection, scene analysis, and spatial relation reasoning. An improved self-attention mechanism was also introduced to enhance small object detection capabilities. [Methods] The proposed method mainly involved ontology model construction, knowledge extraction, and knowledge reasoning. First, an ontology model of construction safety was built based on engineering documents, historical accident reports, and safety hazard reports, with information categorized into six types:entities, attributes, time, space, events, and attribute values, which were represented by normative knowledge. Second, computer vision techniques were employed to detect entities and their attributes and extract spatial relationships between entities. A Mask region-based convolutional neural network (Mask R-CNN) was used for object detection, with an improved self-attention mechanism incorporated to improve small object detection accuracy. As a result, model performance was optimized, and computational complexity was reduced. Finally, a Neo 4j graph database was utilized to store entities and their relationships, enabling automatic recognition of unsafe operations through database queries. In this way, structured reasoning for construction safety knowledge was achieved, and the intelligent level of recognizing unsafe operations was enhanced. [Results] In the experiments, a power engineering construction site was used as the test environment, and six kinds of unsafe operations that could lead to high-altitude falling were selected for simulation experiments. The simulation results indicate that the proposed method outperforms existing approaches in both detection accuracy and training efficiency. Particularly, the improved model demonstrates superior accuracy in small object detection. Additionally, scene segmentation was conducted using a feature pyramid network (FPN) and a unified perceptual parsing (UPP) method, which significantly improved the scene understanding capability of the model. Furthermore, the knowledge reasoning approach based on the Neo 4j graph database effectively integrates entity attributes and spatial relationships, enhancing the automation of unsafe operation recognition. [Conclusion] The proposed method can accurately detect unsafe operations in complex construction environments, thereby improving the intelligence level of construction site safety management. The key innovations of this research are as follows:integrating computer vision with an ontology model to enhance automation in construction safety management; improving the self-attention mechanism by modifying convolutional kernels and introducing a global max-pooling layer, which enhances the small object detection capability of the Mask R-CNN; incorporating the Neo 4j graph database for structured storage and reasoning of construction safety knowledge. This study provides an efficient and scalable solution for the automatic recognition of unsafe operations on construction sites.

[Objective] With the continuous expansion of power grid scale and the increasing complexity of the operating environment, surface corrosion of transmission equipment has become a critical factor threatening the safe operation of power grids. Traditional manual inspection methods are not only inefficient but also struggle to accurately identify subtle corrosion features on equipment surfaces, especially in complex natural environments where the boundaries of corrosion areas are often blurred, posing significant challenges for precise recognition. To address this, a fine-grained recognition method for corrosion areas on the surface of transmission equipment based on image semantic segmentation was proposed, aiming to achieve precise detection and recognition of corrosion areas through deep learning technology. [Methods] The core of this method was the construction of a semantic segmentation network integrated with an attention mechanism. This network, by introducing both channel attention and spatial attention mechanisms, could effectively capture the subtle features and precise boundaries of corrosion areas. Specifically, the channel attention mechanism enhanced the response to channels with prominent corrosion features by analyzing the relationships among various channels in the feature map. Meanwhile, the spatial attention mechanism strengthened the spatial feature representation of corrosion areas by focusing on the spatial location information in the feature map. After the initial segmentation, the K-means++clustering algorithm was employed to perform clustering analysis on the RGB values of the pixels in the segmented images. By optimizing the selection of initial clustering centers, this algorithm effectively avoided the issue of local optimum that could arise with the traditional K-means algorithm, thereby more accurately dividing corroded and uncorroded areas. To further improve recognition accuracy, the structural similarity index was introduced to evaluate each clustered area, and fine-grained recognition of corrosion areas was achieved at the pixel level by calculating the structural similarity between areas. [Results] Experimental results demonstrate that the proposed method exhibits remarkable performance on a dataset of transmission equipment images in complex natural environments, achieving a significantly improved corrosion area recognition accuracy and an obvious improvement in boundary localization accuracy compared to traditional methods. [Conclusion] In summary, the semantic segmentation network integrated with an attention mechanism, combined with the K-means++clustering algorithm and SSIM evaluation, pioneers an efficient and precise new approach for fine-grained recognition of corrosion areas on the surface of transmission equipment. By incorporating the attention mechanism, the proposed method effectively addresses the challenges posed by complex corrosion features and blurred boundaries, significantly enhancing recognition accuracy. Meanwhile, the combination of the clustering algorithm and SSIM evaluation enables pixel-level detailed differentiation, further improving the fineness and practicality of recognition and providing solid technical support for the safe monitoring and maintenance of power grids. Not only does the proposed method ensure the safe and stable operation of power grids, but it also offers valuable insights and inspiration for the application of image recognition and segmentation technologies in other fields.

[Objective] The cost prediction of electric power engineering is of important significance in resource optimization, financial stability, risk management, efficiency improvement, project decision-making, policy formulation, market order maintenance, and investor decision-making for power grid enterprises. To address the problem of poor comprehensive performance of traditional cost prediction methods for electric power engineering, a prediction model based on a gradient boosting decision tree (GBDT) was proposed, with the small sample characteristics of power engineering cost data taken into account. The accuracy of cost prediction was improved significantly by optimizing the residuals generated during the training process. [Methods] The influencing factors of electric power engineering cost were analyzed in depth from both natural environment and technology perspectives. Eleven key variables influencing electric power engineering cost were found, and feature engineering conforming to the GBDT model was constructed through data cleaning, feature encoding, and logarithmic transformation. The hyperparameters were optimized using the Optuna framework, and the model was evaluated using a 5-fold cross validation method. The evaluation index was selected as the goodness of fit in model optimization, and the optimal hyperparameters were iteratively searched for until the prediction accuracy reached the required level or the maximum number of iterations was reached. Finally, a GBDT prediction model combined with the Optuna framework was established. The cost data of substation engineering in an area were taken as an example for experimentation, with 90％ of the data samples used as training and validation sets, and the remaining 10％ as test samples. The prediction results of random forest, neural network, GBDT algorithm, and the GBDT model combined with Optuna were compared, and their performances were evaluated by goodness of fit and root mean square error. [Results] The experimental results show that the prediction performance of the GBDT model combined with Optuna is better than those of random forest, neural network, and GBDT algorithm. The predicted values fluctuate within the range of ±10 CNY/kVA on the basis of the true values, and the goodness of fit reaches 0.892 3, and the root mean square error is 8.01 on the validation set. The goodness of fit reaches 0.886 6, and the root mean square error is 8.09 on the test set. [Conclusion] The cost prediction model of electric power engineering based on a GBDT algorithm can predict electric power engineering cost accurately. Compared with traditional prediction methods, it has higher prediction accuracy, especially suitable for small sample datasets such as electric power engineering cost. Combined with the Optuna framework for hyperparameter optimization, it further improves the accuracy of cost prediction. Subsequent research will collect more sample data and integrate neural network algorithms to achieve better prediction results and promote the efficient operation and healthy development of power grid enterprises.

[Objective] With the global energy transition and the rapid development of clean energy, the penetration rate of high-penetration photovoltaic (PV) sources in distribution networks is increasing. However, PV output power exhibits significant fluctuations and uncertainty due to factors such as solar irradiance and temperature. When a large number of such sources are integrated into distribution networks, they can cause voltage fluctuations, frequency variations, and other issues, presenting significant challenges for power outage fault prediction. Traditional fault prediction methods struggle to accurately capture fault characteristics in complex distribution networks with high PV penetration, leading to reduced prediction accuracy and efficiency, which fails to meet the stability requirements for distribution network operation. [Methods] To improve prediction accuracy and efficiency, this study proposed a fault prediction method for distribution networks with high PV penetration. First, a PV-integrated grid model was built to analyze the impact of PV sources on fault current characteristics in distribution networks. This model clarified how PV sources influence fault current magnitude and distribution under different operating conditions, providing a theoretical basis for subsequent fault zone identification. Next, potential outage zones were inferred by combining grid topology and load imbalance features. The grid topology reflected the connectivity of components, while load imbalance indicated regional load variations. By integrating these factors, the method more accurately localized the fault zone. In addition, power flow entropy was introduced to assess whether circuit loads were in a critical state. Key fault-related power flow features were then extracted from the identified zones. These features were fed into an optimized SA-SAE for training, allowing the system to automatically learn underlying patterns from large datasets and achieve precise outage prediction. [Results] Experimental results demonstrate that the proposed method achieves high prediction accuracy in fault localization for distribution networks with high PV penetration, correctly identifying fault zones (sections 3-6 of the K5-K8 lines) and fault types. Moreover, the average prediction time is only 2.236 seconds, significantly outperforming comparative methods in both accuracy and efficiency. [Conclusion] By comprehensively considering PV integration effects, grid topology, load characteristics, and leveraging power flow entropy and SA-SAE, the proposed method enables high-precision and high-efficiency outage prediction in distribution networks. This method not only enhances prediction accuracy and timeliness, reducing outage risks and economic losses, but also provides robust support for grid planning, operation, and maintenance. It ensures stable distribution network operation and facilitates large-scale integration of clean energy.

[Objective] With the expanding user group of social software, multi-label annotation has been increasingly adopted for text information. How to analyze the behavior and psychology of the user group through data mining of multi-label text information has become a research hotspot. A data mining algorithm for multi-label implicit knowledge based on a deep topic feature extraction model was utilized to enhance text classification accuracy and data mining efficiency. [Methods] To deeply understand the implicit knowledge in text information, the socialization, externalization, combination, and internalization (SECI) theory was employed to convert the implicit knowledge into explicit knowledge. The short-term memory capability of recurrent neural networks was utilized to improve the conversion efficiency. Considering the complexity of text information, local and global features were analyzed separately, and feature fusion was used to improve data mining efficiency. Due to the strong correlation between the context of text information, the gate mechanism of the long short-term memory (LSTM) model was applied to extract contextual dependencies, while the unsupervised latent Dirichlet allocation (LDA) topic model was selected to model the topic structure of the text to mitigate standard differences from manual labeling. Combining LDA-derived global features and LSTM-derived local features, feature stitching was performed to reduce information loss during the feature extraction. A theme controller was introduced to narrow down the inference scope, which obtained more effective text features. Simultaneously, a Gaussian decoder-based contextual topic layer was constructed to calculate the conditional probability matrix of each vocabulary under a given topic, and a Gaussian mixture decoder was used to obtain the conditional probability of the vocabulary. Topic modeling optimization and content expansion were achieved through a Gaussian mixture decoder. Finally, multi-label classification was implemented using the Softmax function to calculate label probabilities. [Results] During model training, perplexity was used as a criterion for evaluation. The proposed model exhibited better perplexity than the control groups (LDA topic model and LSTM model), demonstrating the effectiveness of feature concatenation combining the LDA topic model and LSTM model. By comparing with NVDM, LSTM, LDA, and VAETM models, with precision and recall as evaluation metrics, the proposed model improves precision and recall by 5.05% and 2.75%, respectively. [Conclusion] The comparative experimental results show that the proposed model can significantly improve the performance of text classification. Compared with the LDA topic model and the LSTM model, it outperforms in processing multi-label texts. It can efficiently mine the implicit knowledge in multi-label text data, providing an efficient and accurate solution for tasks such as text classification, semantic analysis, and information retrieval.

[Objective] Remote sensing images, as an important means of Earth observation, are widely used in various fields such as environmental monitoring, resource exploration, and disaster warning. However, remote sensing images are easily affected by sensor noise, atmospheric interference, and other factors during the acquisition process, which leads to a decrease in image quality and blurry details and thus poses significant challenges to subsequent image analysis and target classification. In the task of multi-label remote sensing image classification, traditional supervised learning methods are inadequate with significant classification errors as multiple categories of targets exist in the image, and there may be complex correlations and dependencies between these targets. [Methods] Therefore, to effectively address the impact of remote sensing image noise, accurately capture image features, and improve classification accuracy, a multi-label remote sensing image classification method based on semi-supervised learning was proposed. The remote sensing images were preprocessed using the perceptual loss function. By searching for pixel positions with missing details and blurs in the images, the signal-to-noise ratio residuals of the original and defective images were calculated, and the degree of degradation in remote sensing image quality was determined. A residual mapping based image denoising algorithm was designed, which adjusted the spectral values of noise positions according to the residual mapping values. By adjusting the relationship between high and low frequencies of pixels, the signal-to-noise ratio was improved, and the detailed information in the image was restored. The semi-supervised learning method was used to update and improve the image classifier, which improved the processing efficiency and classification accuracy of remote sensing images, thus achieving the classification of multi-label remote sensing images. [Results] To verify the effectiveness of the proposed method, image classification experiments were conducted at different resolutions and principal component numbers, and classification experiments were designed for different types of remote sensing images. The test results show that the proposed method performs well in denoising and image detail restoration and can clearly distinguish the color blocks in each region, restoring key detail information in the image. In terms of landform feature extraction, its result has a high degree of consistency with the actual landform distribution with only small errors, which proves its advantages in remote sensing image feature extraction. In terms of image classification accuracy, the proposed method achieves a classification accuracy of 0.88 at an image resolution of 70×80 and the principal component number of 12, demonstrating high classification accuracy. Meanwhile, when classifying different types of remote sensing images, the proposed method has a classification accuracy above 0.9 with a maximum of 0.98, which fully verifies its wide applicability and high classification accuracy. [Conclusion] The above results indicate that the proposed method achieves multi-label remote sensing image classification by utilizing an image denoising algorithm that combines the perceptual loss function and residual mapping and a semi-supervised learning method. It not only improves the efficiency and accuracy of remote sensing image classification but also provides new ideas and technical supports for the field of remote sensing image processing, which has higher theoretical significance and practical application value.

[Objective] Substations, as the core hubs of power transmission and distribution, play a crucial role in ensuring the safe and stable operation of power systems, which is essential for efficient and reliable power supply. However, traditional substation monitoring methods face challenges such as limited automatic monitoring capabilities and inadequate target detection accuracy, making it difficult to meet the increasing safety demands of modern power systems. This study aimed to develop substation target recognition and safety monitoring technology based on the regional fully convolutional network (R-FCN) to overcome the shortcomings of traditional monitoring methods, significantly enhance substation safety assurance, and establish a solid foundation for the stable operation of the power system. [Methods] This method combined the unique advantages of region extraction and fully convolutional networks to construct an efficient and intelligent monitoring system. High-definition video surveillance cameras were deployed in the data collection phase to continuously capture real-time image data of the substation from multiple angles, providing massive and precise raw data for subsequent in-depth analysis. The advanced R-FCN model was applied for object detection based on the collected images. Due to its fully convolutional nature, R-FCN could effectively maintain high-resolution feature maps when processing images of different sizes, avoiding the information loss commonly encountered during downsampling with traditional methods, thus significantly improving object detection accuracy. A specially designed area extraction module, resembling an intelligent navigation system, accurately located key facilities such as transformers, switchgear, and insulators within the complex substation environment, ensuring real-time and precise monitoring of equipment status. Moreover, abnormal behaviors, such as unauthorized personnel entering hazardous areas or equipment suddenly emitting smoke or catching fire, were detected promptly, allowing for valuable time to be saved for emergency responses. [Results] Extensive simulation experiments and practical testing in real substation monitoring scenarios demonstrate the system′s excellent performance. In comparison with traditional object detection methods, the system significantly improves detection accuracy, enhances monitoring reliability, and reduces unnecessary manpower and resource expenditure. [Conclusion] The R-FCN-based substation target recognition and safety monitoring technology combines efficient real-time processing and precise target positioning capabilities. When handling massive monitoring data, it can quickly and accurately identify various targets and abnormal situations, providing robust technical support for the safe and stable operation of the power system. This technology has profound implications for enhancing substation monitoring levels and ensuring the reliable power supply of the power system.