Development of GIS Switch State Judgment System Based on Image Recognition

Abstract

Aiming at the fast opening and closing speed of the GIS isolation/grounding switch, manual observation is more difficult, so it is difficult to judge the current switch status. This paper proposes an OpenCV-based image identification algorithm to identify the position of the switch movable contact during the opening and closing process of the isolating switch, thereby judging the state of the isolating switch. This system uses Raspberry Pi as the main hardware core, the server drives the CMOS camera through Raspberry Pi 4B, collects image information in the GIS optical observation window, and performs simple processing, and transmits it to the Raspberry Pi 4B based on the UDP protocol as the main core. In the upper computer and adopt the target detection algorithm based on OpenCV to track the current isolation/grounding switch contact position and determine the current opening and closing state.

Quick Identification of Open/Closed State of GIS Switch Based on Vibration Detection and Deep Learning

“…In order to effectively detect the state of the GIS switch, researchers have proposed a variety of technologies, including image recognition [6][7][8], attitude sensing [9], microswitch [10], magnetic induction [11], current and angular displacement [12], vibration sensing [13] and so on.…”