Research on Transmission Equipment Defect Detection based on Edge Intelligent Analysis. Issue 1 (February 2021)

• Record Type: Journal Article
• Authors: Shen, H M; Fan, P; Wei, Z; Zhao, C; Zhou, S; Wu, Q R
• Is Part Of: Journal of physics. Volume 1828:Issue 1(2021)
• Publication Date: 2021-02
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/1828/1/012087
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: In the transmission system, the continuous load operation and the external environment will make the equipment fault hidden danger, which will affect the stable operation of the transmission system. In this paper, an edge intelligent analysis system of transmission equipment defect image recognition is proposed. The system migrates the cloud image recognition to the edge. Feature Pyramid Network(FPN) is introduced into Single Shot MultiBox Detector(SSD) object detection algorithm based on MobileNet v1 feature extraction network to detect defects of different sizes in large-size, small-size, tower and insulator equipment. So as to realize the rapid positioning of defects and upload the results to the cloud. The results of system application show that the accuracy and recall rate of the proposed system are high. In the case of ensuring the detection accuracy, it meets the real-time requirements of detection. The system can effectively improve the automation level of transmission equipment operation and maintenance. While improving the operation and maintenance efficiency of transmission lines, the safe operation of the transmission system is ensured.