State recognition of circuit breaker based on machine vision

Abstract

In the automatic assembly line of the disconnector, the upper cover and the base of the circuit breaker housing are separated by a separation station. If the upper cover and the base are placed too far apart or placed in the opposite direction, the separation station cannot be separated normally, and it will affect the normal operation of subsequent processes. In this paper, a machine vision recognition and detection system for the circuit breaker shell is proposed. The image of the circuit breaker casing is captured by the CCD camera. The image processing technology is used to detect the edge of the original image of the circuit breaker shell and feature extraction. The algorithm of convex hull is used to calculate the rotation angle. Then the least square method is used to calculate the center position of the largest circle, and the upper cover and the base are identified according to the quadrant of the center of the circle.