Detection of overhead line glass insulator condition using dual function device and deep learning approach

• Published in: COMPUTERS & ELECTRICAL ENGINEERING
• Main Authors: Salem, Ali Ahmed Ali; Lau, Kwan Yiew; Abu-Saida, Ahmed
• Format: Article
• Language: English
• Published: PERGAMON-ELSEVIER SCIENCE LTD 2024
• Subjects: Computer Science; Engineering
• Online Access: https://www-webofscience-com.uitm.idm.oclc.org/wos/woscc/full-record/WOS:001341350500001

This paper presents a design of a multifunction smart wireless device for online condition monitoring of transmission line insulators. The proposed device can measure the insulator leakage current and take images of the high-voltage insulation. Yolov5-based models and deep convolutional neural networks (DCCN) are developed to analyze and classify the measured data and estimate the insulator's health condition. We have developed and tested a prototype of the proposed device. The device can issue a real-time warning message when a sudden change takes place in the leakage current value. The control center or smartphones receive the collected data wirelessly. We analyze the transmitted data using the developed methods to detect any anomalies and take appropriate remedial action. The performance and feasibility of the developed device are assessed through extensive experimental analysis. Results attest to the robustness of the proposed device, which is easy to install for existing and future overhead transmission line insulators.