Research on Surface Defect Detection Method of Photovoltaic Power Generation Panels——Comparative Analysis of Detecting Model Accuracy

Abstract

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.