Transmission Line Fault Insulator Detection Based on GAN- Faster RCNN
Yue Zhang, Yonghui Xu, Lizhen Cui · Research Square · 2023
Abstract Insulators are essential and numerous components in power transmission lines, but they are also prone to faults. Therefore, it is crucial to detect faults in insulators. Although existing fault detection methods for insulators in power transmission lines have been improved to some extent by continuously modifying their internal structures, traditional detection methods still suffer from low accuracy and limited applicability in practical engineering applications. To address these issues, this study proposes an improved Faster Region Convolutional Neural Network (Faster RCNN) network as a generator for detecting insulator defects in power transmission lines. In addition, an adversarial loss is introduced by building a discriminator to enhance the overall detection capability of the original Faster RCNN model. Experimental results demonstrate that our proposed model outperforms existing insulator fault detection models in terms of accuracy.