Recognition of insulator explosion based on deep learning
Feng Gao, Jiao Wang, Zhizhan Kong, Jingfeng Wu, Nanzhan Feng, Sen Wang, Panfeng Hu, Zhizhong Li, Hao Huang, Jianqing Li · 2017
Insulator is an extremely important component of the power transmission system. This article adopts the model of convolutional neural network from recent studies on deep learning to achieve end-to-end intelligent detection of insulators, which helps computers to identify the insulator from the footage faster and obtain fault detection more accurate of the insulator. Firstly, the method of object detection is used to determine the location of the insulator; then the insulator is extrapolated using fully convolutional networks; lastly, based on insulator's fault explosion characteristic, the coordinates of the fault explosion can be detected. The experimental results indicate that the method can effectively detect the faulted insulators in highly cluttered images, and our insulator fault detection outperforms existing methods.