Fault detection of high-voltage insulator thermal images based on YOLOv5

Abstract

In this paper, we propose a defect detection method based on YOLOv5 for thermal images of high-voltage insulators, in which a large number of insulator photographs are taken by a thermal imager, followed by a YOLOv5 model to detect the captured thermal images. The function Meta-ACON is proposed to replace the original activation function. Finally, the extracted features are used for insulator condition identification and defect detection. Experimental findings demonstrate the efficacy of the suggested approach in successfully accomplishing the feature extraction of insulator faults, thus improving the accuracy and efficiency of insulator fault diagnosis.