Open AccessImproved YOLOv4 Power Insulator Fault Detection
Author(s) -
Zhen Zhang,
Shuaihua Kong,
Kun Peng
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2010/1/012148
Subject(s) - insulator (electricity) , electric power transmission , computer science , fault detection and isolation , frame (networking) , power (physics) , fault (geology) , real time computing , transmission (telecommunications) , automotive engineering , artificial intelligence , electrical engineering , telecommunications , engineering , physics , quantum mechanics , geology , actuator , seismology
In order to achieve accurate real-time monitoring of power insulators on transmission lines, an improved YOLOv4 network model is proposed to detect power insulator faults. Experimental results show that the mAP value of the improved YOLOv4 network model reaches 93.01%, and the detection frame rate reaches 44 frames/s. Compared with the YOLOv4 and Faster R-CNN models, it can be concluded that the proposed model can better meet the needs of power insulator fault detection for transmission lines.