Insulator fault feature extraction system of substation equipment based on machine vision

Abstract

AbstractThe artificial intelligence technology and intelligent automation are more and more widely used, the insulators play a supporting and insulating role in the operation of the grid. The use of machine vision inspection technology to detect insulator faults has become an inevitable trend of the times. In this study, based on BP neural network, the fault feature extraction system of substation insulator is studied, and then the system has some shortcomings in target detection algorithm. It then introduced two target detection algorithms, YOLOv3 and Canny, to improve the system. This study then analyses and compares the various indicators. It also analyses some external interference factors that exist when detecting insulator faults. It then further analyses the slenderness ratio of the smallest circumscribed rectangle of the insulator and the background region and the duty cycle of the insulator and the background region. The experimental results show that the recognition rates of both YOLOv3 and Canny target detection algorithms are around 90%. In this study, the influence of external factors is considered, and the fault features are further introduced, so that the true positive rate and accuracy of the algorithm have been improved.