[Objective] Due to the low fault localization accuracy and efficiency of traditional fault self-healing methods, a fault self-healing method for distribution main stations based on the decision tree and multi-agent system (MAS) was proposed to improve the fault handling capability of distribution systems. [Methods] A hierarchical multi-agent technology was adopted to construct a fault self-healing system for distribution main stations, which included the feeder agent and node area agent. The distribution network data were collected and the gradient boosting decision tree (GBDT) algorithm was employed in the node area agent to complete fault localization, and the fault data were transmitted to the feeder agent. In the feeder agent, data were summarized, the influence of important load recovery sequence, transfer margin, and line loss was comprehensively considered to build a fault self-healing optimization model, and the model was solved via the multi-agent evolutionary algorithm to obtain the optimal fault self-healing recovery scheme for distribution main stations. [Results] Based on the IEEE-29 system, experimental analysis was conducted on the proposed method, and the results show that the accuracy of the GBDT fault localization algorithm is nearly 97％ after 150 iteration. The important load recovery amount, network loss, transfer capacity margin, and fault self-healing time of this method are 100％, 90.58 kW, 11.26 kW, and 2.79 s respectively. The self-healing recovery rate exceeds 91％, and the highest self-healing control operation complexity is no more than 5, all of which are superior to other comparative methods. [Conclusions] The GBDT fault localization algorithm can achieve more ideal accuracy and efficiency, and the proposed method can recover all important loads in the shortest time, ensuring minimal network loss. Additionally, the proposed method has relatively stable self-healing ability, which can better coordinate new energy generation, quickly adapt to the rapid development of new power systems, and achieve high-quality power supply. Aiming at traditional fault self-healing methods suffering from problems such as large workload and poor accuracy caused by centralized processing modes, the proposed method constructed a fault self-healing system for distribution main stations based on MAS, achieving fast and accurate fault detection and recovery via the distributed collaboration of the operating status of each node. Compared to the decision tree algorithm, the GBDT algorithm gradually improves analysis accuracy by fitting the residuals of the previous round in each round of iteration to construct a new learner. It is applicable to fault localization at the level of distribution main stations and provides accurate data support for fault self-healing. Compared with traditional optimization methods, the GBDT algorithm adopts the multi-agent evolutionary algorithm to solve the fault self-healing optimization model. By assigning the target to each agent for execution, the optimization efficiency is improved, and the excellent solutions of all agents are summarized to obtain the final solution, ensuring the global optimal effect.

[Objective] Miniature current transformers are a kind of device adopted for current measurement, and their core components are composed of a primary winding, a secondary winding, and a magnetic circuit system. The primary winding is directly connected in series with the measured current circuit, mainly undertaking the task of inducing the magnetic field of the measured current, while the secondary winding is connected to measuring instruments or protective devices, and is employed to output a signal proportional to the primary current. The magnetic circuit system is composed of high-performance magnetic materials, such as high-permeability ferrites or nanocrystalline alloys, which have excellent magnetic properties and can effectively guide and concentrate magnetic fields, ensuring that the transformer can maintain stable performance in complex electromagnetic environments. However, in practical applications, due to the significant nonlinear characteristics of the excitation winding of the miniature current transformer in the saturation region, significant errors will be generated in exciting voltage calculation in conventional linear modeling methods, which seriously restricts the measurement accuracy and stability of the transformer in high-requirement application scenarios such as smart grids. An intelligent detection method for measuring winding errors of miniature current transformers was proposed to improve the measurement accuracy of miniature current transformers and overcome existing technological bottlenecks. [Methods] In response to the nonlinear saturation characteristics of the excitation winding of miniature current transformers, a segmented linearization modeling method was developed to construct an equivalent circuit of the miniature current transformer for acquiring real-time signals of the transformer under the operation status. On this basis, the problem of insufficient applicability of linear models in the saturation region was solved and more accurate data support was provided for subsequent error analysis. A hybrid filtering algorithm combining the Sine Tapers window function and discrete wavelet transform was designed to conduct filtering processing on the acquired signals. Additionally, the Wiener filter and wavelet threshold denoising technology were combined to improve the signal-to-noise ratio, achieve precise separation of high-frequency noise and effective signals, and enhance signal quality. Meanwhile, correlation analysis was conducted on the filtered data, the principal component subspace was extracted via singular value decomposition, and statistical measures were constructed in the residual subspace. Meanwhile, the principal component analysis method was adopted to decompose the signal into the principal component subspace and residual subspace, with statistical measures and contribution rate calculations performed to achieve quantitative detection and accurate positioning of errors. Additionally, expected value operation was introduced to compensate for temperature drift, with fast transient response achieved by error fluctuation modeling, and real-time monitoring and intelligent detection of measurement winding errors realized via combining statistical changes. [Results] The experimental results show that the error detection method for miniature current transformers based on multi-spectral adaptive wavelet filtering and principal component space decomposition proposed in this paper has significant advantages over the traditional methods. Its signal acquisition results have a higher degree of agreement with the voltage current characteristic curve, and show extremely high accuracy in ratio and angle difference detection. [Conclusions] By deeply integrating multidisciplinary technologies, the key technical difficulties in error detection of miniature current transformers are solved, which can achieve highly accurate detection and fast positioning of measurement winding errors of miniature current transformers and improve the measurement stability and safety of power system operation.

A crucial role is played by insulators in providing insulation and mechanical support during the operation of overhead transmission lines. However, in complex and ever-changing natural environments, the surfaces of insulators are highly susceptible to the adhesion of pollutants such as dust and salt, which can result in uneven contamination, seriously alter the electrical performance of insulators, affect their DC flashover characteristics, and increase the risk of flashover accidents on the line, thus causing serious consequences such as power outages, and posing a huge threat to the safe and stable operation of the power system. Therefore, this paper aims to analyze the direct current (DC) flashover characteristics of unevenly contaminated insulators. [Methods] Both the uneven contamination during actual operation by creating an unevenly contaminated insulator model, and the DC flashover process of unevenly contaminated insulators in overhead transmission lines based on electromagnetic field theory were simulated. The two key parameters of non-soluble deposit density (NSDD) and salt deposit density were selected to comprehensively explore the influence of contamination on the flashover characteristics of insulators. Specifically, the content of insoluble contaminants on the insulator surface was reflected by NSDD, while the content of soluble contaminants was reflected by salt deposit density. The adhesion of contaminants on the insulator surface under different contamination levels was simulated by adjusting the wind speed, as the deposition rate and distribution of contaminants on the insulator surface can be affected by wind speed. Additionally, the DC flashover voltage of insulators with different combinations of NSDD and salt deposit density in different wind speed conditions was recorded. [Results] Uneven contamination can cause significant changes to the electric field distribution on the insulator surface, leading to non-uniformity in the originally even electric field. Meanwhile, the too high local electric field strength can increase the possibility of flashover. NSDD formed by non-soluble contaminants can reduce the risk of flashover to a certain extent. This is because although NSDD changes the roughness of the insulator surface, they themselves are non-conductive, thus to some extent hindering the conduction of currents and increasing the flashover voltage. In contrast, soluble contaminants of salt deposit density are prone to form conductive channels in humid environments, thus significantly reducing the insulation performance of insulators and flashover voltage. Analysis was further conducted on the experimental data to verify the accuracy of the analysis results, and the results show that the fitting coefficient is high, indicating sound agreement between the obtained analysis results and the actual situation. [Conclusions] By simulating the influence of wind speed on the contamination situation of the insulator surface, the actual operating environment gets truly reflected, providing new ideas and methods for studying the DC flashover characteristics of unevenly contaminated insulators. Important theoretical basis and technical support are provided by this study for the selection of insulators for overhead transmission lines, the development of anti-contamination measures, and the safe and stable operation of power systems. The incidence of power outages caused by insulator flashover can be reduced and the power supply stability can be improved.

[Objective] Traditional grey models are widely applied to short-term load prediction due to their sound adaptability to small-sample and information-poor data. However, when handling complex electricity consumption data featuring both exponential growth and linear trends, they suffer from inherent limitations, such as insufficient prediction accuracy, sensitivity to data noise, and weak generalization capability, thus making it difficult to meet the demands of modern refined power management. Given the shortcomings of traditional grey models, a comprehensively improved prediction framework was proposed to significantly enhance the accuracy and practicality of electricity consumption behavior prediction, thereby providing more reliable data support for intelligent management of power systems. [Methods] In the data preprocessing stage, the standard deviation method was adopted to identify and remove outliers, while the linear interpolation method was applied to fill missing values in electricity consumption data with dense collection cycles. During the stage of analyzing user consumption behavior, the K-means clustering algorithm was employed to process load curves, and the elbow method was utilized to determine the optimal number of clusters, identifying user groups with similar consumption patterns. In the stage of prediction model building, an improved grey model was proposed to integrate the traditional grey model with a linear regression model for building a fused grey-linear regression model. In the fused model, sequences were generated via accumulation, and fitting was conducted by employing the combined equation, with the parameters estimated via sequence transformation and the least squares method. Meanwhile, the fused model was utilized to predict the residual sequence, and the Fourier transform was introduced for spectral analysis and noise reduction. A Fourier basis matrix was constructed, and related coefficients were solved by adopting the least squares method to correct the original predicted values. [Results] Validation based on the actual data from 205 users in a specific region demonstrates that the improved model successfully identifies four typical electricity consumption patterns by clustering analysis. The proposed improved grey model was compared with the three baseline models of the traditional grey model, the grey model+linear model, and the grey model+residual correction model. The results show that the improved model exhibits significantly lower mean absolute error (MAE) and mean absolute percentage error (MAPE) than the other three models across all user categories and prediction time points. Its advantage is particularly pronounced during the initial prediction periods, indicating that the model is more suitable for short-term load prediction. [Conclusions] Clustering, linear compensation, and Fourier-based residual correction are integrated in the improved grey model. The classification foundation is provided for refined user management by K-means clustering. The traditional model's lack of linear fitting capability is effectively compensated for by linear regression, while noise and systematic errors are significantly reduced by Fourier-based residual correction. A substantial improvement in the model's accuracy and generalization capability is led to by the combination of the three elements. The model demonstrates excellent performance in short-term load prediction, holding practical significance in real-time electric power dispatch, demand response, economical energy usage, and cost reduction. The improved model is mainly applicable to short-term electric power load prediction, and future research will explore the integration with machine learning or the introduction of more factors to enhance its ability for medium-to-long-term electric power load prediction.

[Objective] Power supply side faults in distribution networks are prone to cause three-phase current unbalance, which may further lead to regional power supply interruption and threaten the safe and stable operation of the power grid. Traditional load transfer strategies usually only focus on power balance, without fully considering the impact of negative sequence current distribution on system recovery, which tends to result in disadvantages such as low recovery efficiency and frequent switch operations. To address this problem, aiming at the scenario of power supply side faults in distribution networks, a regional maintenance load transfer method was proposed to achieve efficient grid recovery after faults and optimize load loss, network loss, and the number of switch operations. [Methods] The symmetrical component method was adopted to calculate the negative sequence current in the fault composite sequence network. By comparing the phase difference between the fault phase voltage phasor and the negative sequence current and setting a threshold value, the area to be restored and power outage area were accurately located. After the area division, load transfer was carried out. A multi-objective load transfer optimization model was established, which took the minimization of combined load loss, the number of tie switch operations, and additional network loss as the objectives, with six constraints including topological structure and load controllability set. In view of the conflicts among multiple objective functions, a hybrid algorithm combining genetic algorithm and heuristic search algorithm was used for solution, which could effectively avoid falling into local optimal solutions. Based on the topological analysis and judgment results, available tie switches and preliminary load transfer schemes were searched. Combined with various influencing factors, the hybrid algorithm was applied to obtain the optimal transfer path and generate the best load transfer scheme. By adjusting the states of tie switches, the load was transferred from the area to be restored to the power outage area, which thereby restored power distribution and supply. [Results] To verify the effectiveness of the proposed method, a simulation test was carried out on a 10 kV distribution network in a certain area. The test results show that the average load loss of the proposed method is only 0.215 3 kW, and the additional network loss is relatively small. The minimum number of tie switch operations is only 9 times, and the voltage of each node is generally maintained at a high level, which ensures power supply reliability. [Conclusions] By accurately analyzing the negative sequence current distribution, reasonably dividing the fault-affected areas, and realizing load transfer based on multi-objective optimization, the proposed method effectively avoids the performance trade-off phenomenon in traditional strategies. This method can balance power supply reliability, economy, and rapid recoverability, providing a new technical path for handling power supply side faults in distribution networks, which has significant engineering practical value and popularization prospects. Future research will further combine with dynamic topological reconfiguration and intelligent prediction technologies to enhance its adaptability in complex fault scenarios.

[Objective] Mainly relying on manual inspection, traditional power inspection methods have such problems as low efficiency, high cost, and great danger, and it is difficult for them to meet the requirements of modern power systems for efficient, safe, and intelligent inspection. In recent years, the rapid development of unmanned aerial vehicle (UAV) technology provides a new solution for power inspection. UAVs have the advantages of strong flexibility, wide coverage, and relatively low cost, which can effectively improve the inspection efficiency and reduce the manual inspection risk. However, UAV power inspection systems still face many challenges in practical applications, especially in terms of precise positioning, navigation, and data transmission under complex environments. As a global navigation satellite system independently developed by China, the BeiDou Navigation Satellite System (BDS) has the characteristics of high precision, high reliability and global coverage, providing powerful technical support for UAV power inspection systems. [Methods] By introducing BeiDou satellite technology, a UAV power inspection system that could maintain high precision and stability in complex scenarios was designed to improve the monitoring and maintenance efficiency of power equipment. The core of this paper is to reconstruct the hardware framework of UAV power inspection systems for the deep integration with BeiDou satellite technology. Based on the hardware framework reconstruction, a software algorithm based on the PPP-RTK function model of BeiDou satellite positioning was designed. This algorithm could obtain high-precision position information of UAVs in real time, thus effectively overcoming the influence of complex environments on inspection precision. By implementing this technical route, the stable and precise inspection of UAVs in complex scenarios was realized. In the research process, targeted reconstruction was conducted on the hardware framework to ensure that UAV could stably receive and efficiently process BeiDou satellite signals, and the system performance was fully verified by employing a large amount of experimental data. [Results] The experimental results show that in complex scenarios, the proposed UAV power inspection system can significantly improve the precision and stability of inspection results, and effectively reduce the influence of environmental factors on inspection quality. The effectiveness and superiority of the UAV power inspection system integrated with BeiDou satellite technology in complex scenarios were verified. [Conclusions] By conducting the reconstruction design of the hardware framework and software algorithm optimization, the inspection ability of UAVs in complex environments are notably improved, thus providing more reliable technical support for the monitoring and maintenance of power equipment. The innovation of this paper lies in the introduction of BeiDou satellite technology to the UAV power inspection system, and the realization of high-precision positioning based on the PPP-RTK function model, thereby effectively solving the inspection problem of traditional systems in complex scenarios. This paper not only improves the precision and stability of UAV power inspection but also provides a new technical path for the intelligent and precise monitoring and maintenance of power equipment, which has theoretical and practical significance.

[Objective] Firmware security in power Internet of Things (IoT) devices is crucial for ensuring the stable operation of critical infrastructure. However, existing vulnerability detection methods suffer from limited accuracy and adaptability due to complex firmware characteristics and reliance on a single analysis dimension. To address these issues, a multi-granularity vulnerability detection method for smart power IoT firmware suitable for the ubiquitous IoT background was proposed to improve the comprehensiveness and accuracy of vulnerability detection. [Methods] First, an i2vBi model was designed to map address space operands into eight classes to control the loading base address range, thus accurately generating instruction word vectors. The Softmax function was used to calculate contextual word probabilities, a maximum likelihood estimation model was trained, and instruction vectors were aggregated through a bidirectional long short-term memory (BiLSTM) network to obtain basic block embedding vectors containing forward and backward semantic information. Second, basic block embeddings were used to construct attribute control flow graphs to extract fine-grained structural features within functions. Furthermore, the principal neighborhood aggregation (PNA) algorithm was adopted, combining multiple aggregators and node-degree-based scalers to adaptively aggregate node neighbourhood information, generating more expressive graph embedding vectors and achieving function-level meso-granularity feature extraction. Subsequently, a convolutional neural network (CNN) and a self-attention mechanism were used to extract local pattern features of function execution order from graph embedding vectors, and these sequential features, together with attribute control flow graph features constructed from basic block embeddings, were input into a multilayer perceptron for fusion to form the final comprehensive feature vector. Finally, a semantic analysis dimension was introduced, in which known vulnerable functions were transformed into natural language text. A semantic embedding model based on bidirectional encoder representations from transformers (BERT) was used for masked modeling and mean pooling to generate semantic vectors. The cosine similarity between the semantic vectors and the comprehensive feature vectors of target functions was computed, and multi-granularity vulnerability detection based on semantic similarity was achieved by setting a threshold. [Results] To verify the effectiveness of the proposed method, experiments were conducted on a dataset containing real power IoT firmware images. The experimental results show that the AUC value of the proposed method remains stable between 0.85 and 0.95, which is significantly higher than that of comparative methods, demonstrating excellent overall classification performance. The Kappa coefficient lies in the high range of 0.85-0.95, indicating a high degree of consistency between detection results and actual conditions. The Hamming distance remains at a low level, indicating that false positive and false negative rates are effectively controlled, and prediction results are more accurate. [Conclusions] The proposed method effectively overcomes the limitation of a single feature dimension by integrating multiple levels of features, including instructions, basic blocks, function control flow, and semantics. This method not only significantly improves the accuracy and robustness of vulnerability detection but also exhibits better environmental adaptability due to its understanding of code semantics. The research results provide a reliable technical approach for automated and intelligent security analysis of smart power IoT firmware and have positive significance for enhancing the overall security and stability of power IoT systems.

[Objective] The size and needs of the visually impaired groups cannot be ignored. The application of tactile sensing in the field of assisted reading is particularly noteworthy. This technology can not only be integrated into robots or prosthetic systems, but also provide an effective braille reading tool for blind or visually impaired groups. Therefore, research on vision aids and braille recognition technology with information interaction competency is significantly valuable for offering technical support for visually impaired groups. [Methods] Based on biomimetic principles, the function of biomimetic hair was simulated. With magnetic iron-gallium wire as biomimetic hair and Hall elements as receptors at the hair roots, a biomimetic electromagnetic tactile sensor was designed according to the size of braille dots. Based on magnetization intensity and magnetic induction intensity theories as well as mechanical equations, the relationship curve between the sensor's applied force and output voltage was deduced. A dynamic characteristic testing system was constructed, which consisting of a signal generator, a power amplifier, a vibration exciter, data acquisition card, a computer and a direct current stabilized voltage supply. The dynamic characteristics of the tactile sensor were tested. [Results] Test results show that the tactile sensor can convert applied force into an electrical signal within the range of 0-1.5 N. Within the applied force range of 0-1.5 N, the output voltage gradually increases with higher force. When the contact force is less than 0.5 N, the two approach a linear relationship. The sensor exhibits high stability in output voltage under an applied force of 0.2-1.4 N at a frequency of 1 Hz. Under an applied force of 1.0 N at 1 Hz, its sensitivity is 34.5 mV/N. When the applied force is 0.5 N at 1 Hz, the response time and recovery time are 20 ms and 18 ms, respectively. The designed biomimetic electromagnetic tactile sensor was applied to establish a braille recognition system consisting of a two-finger robotic hand, a motor-driven slide, a data acquisition card, and a computer. The correspondence between braille letters and the output voltage waveform was determined by scanning the braille dots. [Conclusions] The output characteristics of the developed biomimetic electromagnetic tactile sensor were tested. The experimental results show good agreement with the calculated values, indicating that the calculated model can describe the relationship between the applied force and the output voltage. The designed tactile sensor features high stability, high sensitivity, and fast response speed, making it suitable for detecting both static and dynamic applied forces. The braille recognition system was used to determine the voltage waveform corresponded to the braille letters. It is pointed out that voltage waveform peak count, peak intensity, and peak initiation time can serve as the criteria for recognizing the braille letters, demonstrating that the braille recognition system can recognize braille letters. The research results can provide new braille recognition tools and technical pathways for visually impaired groups, allowing for the deep integration of tactile sensors and recognition technology to build assistive technology support systems for visually impaired groups.

[Objective] A substation cost prediction model based on an improved long short-term memory (LSTM) network, spatio-temporal long short-term memory (ST-LSTM) network, was proposed to address the limitations of existing substation cost estimation methods in terms of prediction accuracy and computational efficiency, thus improving the cost prediction accuracy and efficiency. Based on building information modeling (BIM) data, a dual-stream memory conversion mechanism and ZigZag spatio-temporal memory flow are introduced in the model to effectively capture and learn the complex dynamic features in spatio-temporal data, thereby achieving unified modeling of the short-term spatial detail changes and long-term temporal dynamic evolution process. [Methods] Firstly, BIM cost data were preprocessed, including data cleaning, standardization, and time series division, to ensure data integrity and usability. Then, the ST-LSTM network model was built. By improving the triple gating mechanism of traditional LSTM networks, the ZigZag spatio-temporal memory flow and dual-stream memory conversion mechanism were introduced to enhance the model's ability to extract and fuse spatio-temporal features. At the model training phase, the grid search method was adopted to optimize the number of hidden layer neurons, mean square error (MSE) was employed as the loss function, and the Adam optimizer was combined to complete the updating of model parameters. In the experiment, the actual BIM cost data from 105 substations were selected and divided into the training set, validation set, and test set in a 3∶1∶1 ratio for model training and performance evaluation. [Results] By carrying out multiple rounds of simulation experiments, the prediction performance of the ST-LSTM network model, particle swarm optimization (PSO) algorithm, and traditional LSTM network model was compared and analyzed. Additionally, the mean absolute percentage error (MAPE), root mean square error (RMSE), and Pearson correlation coefficient were adopted as the evaluation indexes. The results show that the highest accuracy of the ST-LSTM network model is approximately 95％ in short-term prediction and more than 90％ in long-term prediction, and its overall average prediction accuracy exceeds 90％. Thus, this model significantly outperforms the PSO algorithm and traditional LSTM network models. In terms of computational efficiency, the average running time of the ST-LSTM network model is 1.1 s, slightly longer than 0.5 s of the PSO algorithm but shorter than 1.2 s of the traditional LSTM network model. However, the values are all within an acceptable range of engineering applications. Further analysis reveals that the ST-LSTM network model demonstrates more significant prediction advantages when dealing with large-scale datasets characterized by complex spatio-temporal features. [Conclusions] The substation cost prediction method based on the ST-LSTM network model can effectively extract and fuse multidimensional spatio-temporal features, significantly improving the accuracy and overall computational efficiency of short-term and long-term cost prediction. Compared with the PSO algorithm and traditional LSTM network models, the ST-LSTM network model has a significant advantage in prediction performance, but its computational complexity is relatively high, thereby putting forward higher requirements for computing resources and training time. Future research will focus on model structure optimization and computational complexity reduction to enhance the model's application feasibility and promotional significance in engineering practices.

[Objective] Aluminum alloys have become one of the most widely employed non-ferrous metal materials in the industrial field due to their low density, high specific strength and stiffness-density ratio, excellent corrosion resistance, and sound toughness, and are indispensable basic materials in many key fields till now. In the wide variety of aluminum alloys, for the aluminum-silicon alloys, the mechanical properties and comprehensive utilization properties of alloys are significantly improved by the addition of silicon, thus making the aluminum-silicon alloys gain the most widespread application. Therefore, it is always a research hotspot to study the modification, and the application and development of aluminum-silicon alloys of different grades. Laser additive manufacturing (LAM) technology features a high level of automation and short forming cycles, becoming an important direction of advanced manufacturing, with laser melting deposition (LMD) gaining widespread application due to its unique advantages. However, the mechanical properties of aluminum-silicon alloys' parts prepared by LMD cannot meet the stringent requirements of high-end applications. To this end, the effect of Yb on the microstructure and properties of AlSi12 alloy under LAM was studied, and the suitable amount of added Yb was explored. [Methods] The experimental specimens were prepared by employing the LMD-8060 device by adopting the short-side one-shot sequential scanning strategy and combining various parameters. Meanwhile, the effects of Yb with different mass fractions on the microstructure and properties of AlSi12 alloys were systematically analyzed by adopting analytical instruments such as the optical microscope, scanning electron microscope, X-ray diffractometer (XRD), and universal tensile testing machine. [Results] The results show that a suitable amount of Yb can refine the primary α-Al grains, and metamorphose the eutectic silicon at high temperature and high cooling rate. When the Yb content ranges from 0％ to 0.3％, the morphology of primary α-Al is gradually changed from columnar crystals to equiaxed crystals, and the eutectic silicon is transformed from irregular sharp flakes to rounded particles, with a notable increase in the particle number. Meanwhile, under the Yb content of 0.3％, twin and double twin structures are observed. When the Yb content is in the range from 0.3％ to 1.0％, the primary α-Al and eutectic Si are further refined, but the eutectic microstructure shows a large-sized massive Si phase, which is embedded in the aluminum matrix in the shape of a cube. Additionally, XRD analysis shows that there is a very few amount of the second phase YbAl₂Si₂ in the alloy, which may be the result of rapid cooling and solidification. EDS analysis reveals that Yb has an alloy-strengthening effect on the AlSi12, which is mainly via the method of solid solution strengthening. In terms of mechanical properties, the tensile strength of the alloy shows a trend of increasing and then decreasing with the rising Yb content. The tensile strength reaches the maximum value (208.71 MPa) under the Yb content of 0.3％, while decreasing to the minimum value under the Yb content of 1.0％. Excessive Yb is prone to alloy embrittlement and the production of a large number of defects inside. [Conclusions] Comprehensive microstructure and property analysis shows that the optimal addition amount of Yb is about 0.3％ for AlSi12 alloy, which can effectively improve its microstructure and mechanical properties to meet the property requirements of LAM for aluminum-silicon alloy.

[Objective] This study aims to investigate the effects of different thermal exposure time on the microstructure, surface oxidation behavior, and fatigue properties of Ti65 alloy under 600 ℃ thermal exposure conditions, and clarify the mechanism underlying the influences of precipitated phase evolution and surface oxide layer formation on the fatigue life of the alloy during thermal exposure. [Methods] The Ti65 alloy was thermally exposed at 600 ℃ for 55, 100, 500, 1 000, and 2 000 h, and the microstructure and surface oxidation behavior of the Ti65 alloy before and after thermal exposure were characterized. The rotating bending fatigue tests were conducted on the Ti65 alloy before and after thermal exposure to obtain the fatigue life under the condition of 650 ℃ and 401 MPa. [Results] The microstructural composition of the Ti65 alloy before and after thermal exposure is basically consistent. With the increase of thermal exposure time, the size and content of the primary α_p phase and the lamellar width of the secondary lamellar α_s phase show no significant changes, while the size and content of the α₂ phase and silicides increase to some extent. The thickness of the oxide layer is approximately 540 nm when the thermal exposure time reaches 2 000 h. Additionally, thermal exposure significantly increases the surface roughness of the specimen. Furthermore, as the thermal exposure time prolongs, the number of specimens capable of reaching the fatigue limit (10⁷) exhibits a trend of increasing first and then decreasing, indicating that the fatigue stability initially improves and subsequently deteriorates. [Conclusions] Analysis indicates that during thermal exposure at 600 ℃ , an oxide layer forms on the surface of the Ti65 alloy specimen, and oxygen elements diffuse into the matrix, creating an oxygen diffusion layer. On the one hand, the formation of oxide particles during thermal exposure increases the surface roughness of the specimen. On the other hand, the oxide layer is primarily composed of ceramic-like brittle oxides. Both factors contribute to stress concentration, making fatigue cracks more likely to initiate under cyclic loading, thereby reducing the fatigue life of the Ti65 alloy. Simultaneously, during thermal exposure, the size and content of the α₂ phase and silicides increase, enhancing their hindrance to dislocation motion. Overall, the fatigue properties of the Ti65 alloy are primarily influenced by the combined effects of precipitated phase evolution and surface oxide layer formation during thermal exposure, with a competitive relationship between the two. In the early stage of thermal exposure, the formation of the precipitated phase plays a dominant role, increasing the number of specimens that can achieve the fatigue limit as thermal exposure time prolongs. When the thermal exposure time reaches 100 h, the number of specimens reaching the fatigue limit peaks. As the exposure time is further increased, the influence of the surface oxide layer gradually becomes dominant, leading to a gradual reduction in the number of specimens capable of achieving the fatigue limit.

[Objective] In harsh sea conditions, due to the influence of wind, waves, and other factors, the ship deck is in constant motion. In such conditions, a stable and independent landing is difficult to achieve for unmanned helicopters. Generally, the operator's experience should be relied on to achieve remote control landing. This landing method is time-consuming and has great safety hazards. Therefore, it is urgent to predict the amplitude of the roll, pitch, and ascending and descending, and the motion change rate of the ship deck for determining the optimal landing time when the unmanned helicopter can land the ship safely and stably, thus reducing landing risks. [Methods] The autoregression model was employed to model and predict the motion state of the ship deck based on the time series prediction algorithm, thus predicting the optimal landing time of the unmanned helicopter. On this basis, a multi-objective optimization mathematical model was built to meet the safety requirements during the landing of the unmanned helicopter, with the simulated annealing optimization algorithm adopted to calculate the optimal landing to provide a decision-making basis for the independent landing of unmanned helicopters. Meanwhile, a ship deck motion simulator was developed to simulate the roll, pitch, ascending and descending motion of the ship deck, with an adaptive gear system built to simulate the landing process and verify the optimization results. [Results] The experimental results indicate that the predicted data curve is highly consistent with the measured data curve. The maximum error between the predicted roll and pitch values and the measured values is less than 0.01°, and the maximum error between the predicted ascending and descending values and the measured values is less than 6 mm. The maximum relative error is less than 1％, which meets the requirements for prediction accuracy. The optimization results based on the simulated annealing algorithm show that 91.50 s, 96.75 s, and 99.25 s are the key moments when the roll, pitch, ascending and descending amplitudes of the ship deck and their motion change rates are small. Specifically, the comprehensive tilt angle of the deck is the lowest, and the motion change rate is the smallest at 91.50 s, which is the time for the unmanned helicopter to stably land. [Conclusions] The prediction algorithm for deck motion state based on the autoregression model features high prediction accuracy and fast response speed. Additionally, it can efficiently calculate accurate deck motion data. Compared with the traditional prediction methods, multi-objective optimization was conducted on prediction results by adopting the simulated annealing algorithm, and the selected optimal landing time can better meet the requirements for safe and stable landing of the unmanned helicopter. This study not only improves the safe landing ability of unmanned helicopters under complex motion states of ship decks, but also provides references for the take-off and landing of other types of aircraft.

[Objective] Laser heat-assisted grinding can significantly improve the processibility of titanium alloys, with the laser preheating temperature field directly affecting the surface quality and grinding force of the workpiece. To reveal the laser-assisted belt grinding mechanism of titanium alloys, the influence laws of laser processing parameters on temperature field distribution and grinding force were investigated. [Methods] Based on heat conduction theory, a laser preheating simulation model of titanium alloys was established using finite element simulation software. The effects of laser power, scanning speed and spot radius on the workpiece temperature field distribution were analyzed. According to the micro-abrasive grinding theory, a laser-assisted single-abrasive grinding simulation model of titanium alloys was constructed to study the variation of grinding force under different preheating conditions. Additionally, laser-assisted belt grinding experiments of titanium alloys were designed to verify the simulation model. [Results] The laser absorption rate of titanium alloy was determined by comparing the experimentally measured temperature with the simulation results, thus further improving the laser preheating simulation model of titanium alloys. The simulation results of the laser preheating temperature field show that the temperature of the laser preheating zone goes up with the rise of laser power and decreases with the increase of the moving speed of the laser relative to the workpiece. When the workpiece moving speed is relatively low, the influence of speed variation on the preheating temperature is minor. The spot radius gets smaller with the higher temperature of the preheating zone, as a smaller spot radius leads to more concentrated laser energy and a higher temperature rise per unit time under the same laser power. The simulation results of laser-assisted single-abrasive grinding show that the grinding force decreases with the increase of laser power, because higher laser power leads to the elevated material temperature and reduced hardness of the grinding layer, thus lowering the processing resistance. The comparison between simulation and experimental results shows an average relative error of about 4.95％, indicating their good agreement and high reliability of the simulation model. [Conclusions] Laser irradiation can induce a sharp temperature rise on the material surface, forming an oxidized deteriorated layer. Due to the low thermal conductivity of titanium alloys, significant thermal stress can be generated by a large temperature gradient, which promotes the formation of microcracks in the preheating layer. If the deteriorated layer and thermal cracks induced by laser preheating are not removed by grinding, the workpiece surface quality will deteriorate. The established finite element simulation model is in high agreement with the experimental results, which verifies its reliability and accuracy, providing a reference for other laser-assisted material removal processes.

[Objective] With the rapid development of the industrial internet, detecting abnormal traffic in network data streams has become a critical task for ensuring network security. Traditional machine learning models struggle with feature extraction and generalization, making it difficult to handle high-dimensional, diverse, and massive network traffic data. To address these challenges, this study proposed a novel abnormal traffic detection method combining a simple recurrent unit (SRU) with an improved residual network (ResNet). This method aims to enhance detection accuracy and efficiency through spatiotemporal feature extraction while mitigating issues such as overfitting and the gradient vanishing problem, thus offering a more efficient and reliable solution for network abnormal traffic detection. [Methods] A deep learning model integrating SRU and the improved ResNet was constructed. The SRU network handled data screening and temporal feature extraction, enabling efficient parallel computation via reset and forget gates, which significantly boosted training speed. The improved ResNet adopted an atrous residual structure, expanding the receptive field with atrous convolution to enhance feature extraction and alleviate gradient vanishing. By combining these networks, both spatial and temporal features of network traffic data were captured comprehensively. Experiments were conducted on the KDD Cup 99 dataset for binary classification to evaluate the model's performance. [Results] The experimental results show that the ResNet-SRU model achieves a classification accuracy of 98.89％ and a precision of 98.66％ on the KDD Cup 99 dataset. Compared to methods such as CNN-LSTM, ResNet-GRU, and CNN-GRU, it achieves approximately a 1％ improvement. During training, the model demonstrates faster convergence and superior stability. It outperforms comparative models in accuracy, precision, recall, and AUC, highlighting its effectiveness and robustness in abnormal traffic detection. Although training and testing times are slightly longer, the significant improvement in detection performance justifies this trade-off. [Conclusions] The abnormal traffic detection method based on ResNet and SRU shows remarkable advantages in processing high-dimensional network traffic data. By integrating the advantages of atrous residual structures for spatial modeling with SRU's temporal feature extraction, it effectively overcomes the limitations of traditional models in feature extraction and generalization, enhancing detection accuracy and efficiency. However, the model's parameter scale and computational cost still require optimization. Future research will focus on lightweight model design, improving detection performance for imbalanced samples, and further reducing computational overhead to enhance its practical application value.

[Objective] Grey prediction models are widely applied in diverse fields due to their simple structure, desirable accuracy, and low dependence on data volume. However, conventional models have flaws like overly steep prediction sequences, inaccurate relationship representations, and the distortion in prediction results caused by extreme values. To improve prediction accuracy, this paper fully accounts for external factors affecting the system, refines the grey prediction model, and optimizes its solution structure, thus presenting a new nonlinear fractional-order multivariate discrete grey prediction model NFMDGM(1,N). [Methods] Based on the optimized grey prediction model OGM(1,N), this model substituted fractional-order differential equations and fractional-order cumulative generation for the traditional integer-order cumulative generation to effectively improve the model's generalization and adaptability. Simultaneously, the smoothing generation method was introduced to deal with the system influencing factor sequence, enhancing the model's robustness and accuracy. For the solution of the smoothing generation parameter and the fractional-order parameter in the prediction model, a solution framework based on the improved whale optimization algorithm (IWOA) was devised. Given that the traditional whale optimization algorithm (WOA) was sensitive to the original data and prone to local optima, this paper used chaotic mapping to generate the initial population to ensure its uniform distribution. Moreover, inertia weights and nonlinear functions were introduced to refine the control parameters, thus enhancing both global and local search capabilities. The mean absolute percentage error (MAPE) was served as the objective function to solve the optimal parameters required by the grey prediction model. The construction process of the NFMDGM(1,N) model was detailed in the paper, and the time response equation and unbiasedness of the model were strictly proven. The model parameters were determined to ensure the model's effectiveness. [Results] In the performance test of the IWOA, six benchmark functions were selected for testing and compared with the traditional WOA and some common intelligent algorithms. The results show that the IWOA performs better in convergence speed, solution accuracy, and stability, and is more suitable for solving the parameters of NFMDGM(1,N). To verify the effectiveness of the proposed model, the Australian power load dataset was used to compare NFMDGM(1,N) with OGM(1,N) without innovation points and some common prediction models. Using the MAPE as the test standard, the results of the new model in the training set and the test set are 0.135 and 0.634 respectively, which are lower than those of other prediction models. The prediction results are more accurate, and the advantage of the grey model becomes particularly evident in small sample forecasting. [Conclusions] The innovation of this paper lies in the construction of a new NFMDGM(1,N) model, integrating multiple improvement strategies to effectively handle small sample data. The WOA is optimized to enhance the parameter solution performance, providing a more accurate method for small sample prediction. The new model is helpful for adjusting the power supply and demand plan in power load prediction and also opens up new ideas and methods for the research of grey prediction models and optimization algorithms.

[Objective] Bridge structures are prone to varying degrees of damage due to prolonged exposure to vehicle loads, environment, and other factors. Such damage compromises structural safety and functional integrity, with severe cases potentially leading to catastrophic collapse. Regular damage identification during bridge operation enables timely detection of defects, facilitates targeted repairs, and mitigates risks of accidents, casualties, and economic losses. Consequently, developing precise and efficient damage identification methods is pivotal to ensuring transportation safety and advancing structural health monitoring technologies. [Methods] Existing damage identification approaches often face limitations due to stringent requirements for environmental stability, sensor density, and measurement accuracy, alongside complex operational workflows. To simplify the process of main girder damage identification, a mechanical model was established for post-damage bending stiffness and deflection detection values according to the mechanical relationship between deflection and bending stiffness, with which the change law of girder bending stiffness in the presence of damage was revealed. The degree, location, and extent of bending stiffness damage at any position of the main girder can be identified only with measured post-damage deflection values. [Results] After comparing and analyzing the bending stiffness curves of the main beam before and after damage, it is found that after the main beam is damaged, its bending stiffness curve will have a step-shaped drop mutation at the damaged part. According to the mutation condition, the damage information of the main beam can be identified, that is, the position of the mutation drop section of the main beam bending stiffness curve is the damage location of the main beam, the length of the drop section is the damage range, and the number of drop sections is the damage quantity. Furthermore, the section length of the main girder determines damage identification accuracy. Loaded regions are divided according to the loading tool length, while non-loaded regions are partitioned into sections measuring 1/10 to 1/20 of the girder length. [Conclusions] The proposed method accurately identifies bending stiffness distributions under both intact and damaged conditions, even for scenarios involving extended and continuous damage. It simplifies data acquisition, reduces inspection costs, and enhances operational feasibility. This study offers actionable insights for advancing bridge damage identification technologies.

[Objective] Early-age hydration heat in mass concrete produces temperature gradients and tensile stress, yet current assessments often rely on three-dimensional finite element (FE) analysis and field stress monitoring, making it difficult for rapid quantitative assessment in construction scheme comparison. To address this issue, a fast prediction approach considering environmental factors was proposed for hydration-heat-induced damage. [Methods] Based on the heat-conduction equation and continuum damage mechanics, an explicit prediction chain was established, namely, “maximum temperature difference prediction-temperature difference distribution-thermal strain-damage evolution”. The adiabatic temperature rise, ambient temperature, placement temperature, water-cement ratio and pouring-layer thickness were selected as key variables. A coupled parameter ω was introduced based on the characteristic length scale of heat diffusion to represent the synergistic effect of mix proportion and geometry on heat accumulation. The coefficients were calibrated by 15 parametric FE cases. The through-thickness temperature difference distribution was approximated as an exponential distribution and the error comparison was carried out along representative paths. The damage variable was defined as a stiffness-degradation index, and its correspondence to microcracking and macrocrack initiation was clarified. [Results] When the adiabatic rise is from 50 ℃ to 70 ℃, ambient temperature is from 12 ℃ to 28 ℃, placement temperature is from 10 ℃ to 30 ℃, water-cement ratio is from 0.30 to 0.40, pouring-layer thickness is from 2 m to 3 m, the predicted maximum temperature difference shows a correlation coefficient of R²=0.96 with FE results, with the correlation for temperature difference distribution greater than 0.94. The predicted damage distribution matches the high-risk zones calculated by FE and identifies a potential crack-prone region within about 1.2 m from the exposed surface (condition 15). [Conclusions] The proposed model is a parametric explicit calculation model applicable for rapid comparison of temperature-control schemes and cracking risk zoning. Within the above-mentioned parameter range, the model coefficient completes the calibration. For conditions beyond the range, recalibration using monitoring data or additional samples is recommended.