Automatic detection method for partial discharge of switch cabinet based on multi-vision system

Abstract

The invention discloses an automatic detection method for partial discharge of a switch cabinet based on a multi-vision system. The automatic detection method comprises the steps that a robot autonomously moves along a navigation route according to navigation marks laid in a switching station, and the robot stop in front of a switch cabinet to be detected when a stop mark is detected; target location is completed according to shape features, which are acquired by a binocular vision system, of a target, then three-dimensional coordinate calculation for related points in an image is completed based on feature point matching and a parallax principle; movement of a mechanical arm is controlled so as to enable the tail end of the mechanical arm to carry partial discharge detection equipment to reach the position of a target point, pixel deviation of a target area is calculated by using an image taken by a monocular camera arranged at the tail end of the mechanical arm, and position correction is carried out on the mechanical arm according to coordinate position deviation of the target; and different modes of partial discharge detection are carried out on the switch cabinet. According to the invention, a binocular vision system and monocular vision system combining target positioning method is adopted, accurate positioning for a partial discharge detection target is realized, and the error caused by single vision system positioning is reduced.

Description

technical field [0001] The invention relates to an automatic detection method for partial discharge of a switch cabinet based on a multi-vision system. Background technique [0002] With the advancement of science and technology and the continuous development of the two first-class constructions, the construction of smart grids characterized by "informatization, digitization, automation, and interaction" has gradually deepened. New Technology Catalogue, the substation intelligent inspection robot has entered the stage of promotion and application. In 2013, functions such as routine inspection, meter transcription and automatic storage comparison analysis, bad weather inspection, infrared precise temperature measurement, background automatic archive analysis and other functions were carried out, which effectively improved the efficiency and benefits of substation inspection and reduced the workload of frontline employees in the grassroots team. workload. With the continuous...

AI Technical Summary

Problems solved by technology

[0003] First, the function of the substation intelligent inspection robot is limited. The robot can only perform inspection tasks outdoors, and its functions are limited to the detection of infrared thermometers and visible light cameras. The partial discharge detection of indoor electrical cabinets and switchgear equipment is only limited. It can rely on manual inspection, but it cannot be realized in robot inspection;

[0004] Second, the navigation methods of inspection robots in existing substations mainly rely on magnetic navigation and laser navigation. These two navigation methods are costly, inflexible, and have certain requirements for the detection environment;

The robotic arm system based on binocular visual servo is affected by equipment positioning accuracy, control accuracy, and mechanical errors, resulting in an error between the final docking position of the end of the robotic arm and the actual detection position, which affects the quality of the robotic arm's work.

Images