INTRODUCTION: Research on intelligent defect detection technology using machine vision was conducted to address the challenging problem of detecting and localizing PV defects in photovoltaic power generation system operation and maintenance.OBJECTIVES: The aim is to improve the accuracy of PV defect detection and enhance the operation and maintenance efficiency of PV power plants.METHODS: In this paper, three detection methods such as image processing based detection, traditional machine learning based detection, and deep learning algorithm based detection are discussed and compared, and analyzed respectively. It is finally concluded that the deep learning based detection is more efficient in comparison. Then further analysis and simulation experiments are done through several detection algorithms based on deep learning.RESULTS: The experiment yields a high accuracy of the detection model based on the Faster-RCNN algorithm. Its mAP value reaches 92.6%. The detection model based on the YOLOv5 algorithm reaches a mAP value of 91.4%. But its speed is as much as 7 times faster than the model based on the Faster-RCNN algorithm.CONCLUSION: Comprehensive speed and accuracy index. Combining the needs of PV defect detection in the operation and maintenance of PV power generation systems with the results of simulation experiments. It is concluded that the detection model based on the YOLOv5 algorithm can provide better detection capability. Modeling with this algorithm is more suitable for PV defect detection.

For the instability problem of the wind turbine flexible tower caused by mechanical fatigue and vibration, Back Propagation (BP) neural network is used to establish the tower vibration prediction model to solve the wind turbine tower vibration prediction analysis. To find correlation association factors impacting the flexible tower vibration, the multi-source heterogeneous data from various operating situations of wind turbines are optimized using correlation analysis. A BP neural network-based tower vibration prediction model is created. The findings of a simulation investigation using data from a wind farm’s 2 MW wind turbine with a 120 m flexible tower reveal that the BP neural network has the greatest predictive power for operating situations below the rated wind speed. The root mean square error RMSE decreased by 10.6608; the mean absolute error MAE decreased by 9.1915 compared to the above rated wind speed. It is proved that the BP neural network prediction model has high accuracy in predicting the vibration of the flexible tower for working conditions below the rated wind speed, which can provide accurate data support for the vibration control of the flexible towers.

The early and accurate recognition of fruit tree pests and diseases is essential for safeguarding fruit yield, quality, and sustainable agricultural production. Conventional manual inspection methods are inadequate for meeting the demands of continuous, objective, and real-time monitoring in large-scale orchards. Following the framework of “model evolution–key challenges–edge-intelligent deployment,” this review systematically summarizes advances in deep learning-based recognition of fruit tree pests and diseases, and compares the effectiveness and limitations of representative methods from the perspectives of data complexity, model generalization and robustness, real-time inference, cross-modal fusion, and trustworthy diagnosis. Existing studies indicate that CNNs, attention mechanisms, Transformers, multimodal fusion, and lightweight networks have promoted the transition of fruit tree pest and disease recognition from image classification to object detection, lesion segmentation, and edge deployment; however, sample scarcity, class imbalance, insufficient cross-domain generalization, black-box decision-making, energy constraints, and long-term robustness remain major bottlenecks for field application. Future research should focus on open orchard environments and develop data-efficient, interpretable, low-power, and continuously updatable edge-intelligent recognition systems, thereby advancing precision agriculture and smart orchards.

Based on the principle of electromagnetic induction, this paper proposes a new sleeve structure of electromagnetic induction heating energy storage system, which converts the electrical energy that cannot be consumed by wind power, solar power and other power grids into heat energy. The electromagnetic induction heating model of the eddy current field is established by Ansoft/Maxwell, and the magnetic induction intensity, current penetration depth and current frequency are analyzed. The three-dimensional fluid temperature field and its corresponding temperature characteristics of the system are analyzed by Ansys/Fluent. The temperature field cloud diagram of the sleeve is analyzed. It is concluded that with the increase of air thickness, the loss of the internal iron pipe increases, and the loss of the middle iron pipe decreases. The characteristic curve of the resonant circuit of the electromagnetic induction heating power supply is simulated and analyzed to determine the optimal parameters of the resonant circuit of the induction heating. A 100 kW electromagnetic energy storage system is developed, and the effectiveness and practicability of the method are verified, which can be applied to high power thermal energy storage.