Substation knife switch temperature detection method based on unmanned aerial vehicle bifocal image fusion

Abstract

The invention discloses a transformer substation knife switch temperature detection method based on unmanned aerial vehicle dual-light image fusion, which comprises the steps of identifying a knife switch in a visible light image for one group of detection objects, and marking a local image of an area where each identified knife switch device is located by adopting an identification frame; recognizing the edge contour of the knife switch equipment in each local image, and obtaining the position information of each switch contact point in the visible light image according to the characteristicsof the edge contour of the knife switch equipment; calculating to obtain position information of each switch contact point in the infrared image by combining a mapping relationship between the visible light image and the infrared image in the same group of detection objects; and calculating to obtain temperature information of each switch contact point in the infrared image. According to the invention, the disconnecting link identification and temperature detection speed in the infrared picture is improved, the temperature detection result can be obtained more quickly, possible faults or abnormal conditions can be handled and dealt with more timely, and the overall detection efficiency of the temperature of the disconnecting link of the transformer substation is improved.

Description

technical field [0001] The invention relates to the technical field, in particular to a temperature detection method for a substation switch based on dual-light image fusion of a drone. Background technique [0002] With the continuous development of UAV technology, UAV products are becoming more and more mature, and the scope of application is becoming wider and wider, including military operations, geological surveys, logistics and transportation, agricultural applications, film and television shooting, fire fighting and disaster relief, and rescue inspections, etc. Many fields. The application of drones in power system transmission line inspections and substation inspections has been fully launched, and it is changing from manual drone inspections to fully automatic unmanned inspections. Compared with high-voltage transmission lines, substations require smaller inspection sites, and there are more various substation equipment and switchgear, so the inspection frequency i...

AI Technical Summary

Problems solved by technology

As can be seen from the foregoing, this method uses a binocular camera to calculate a 3D point cloud, incorporates temperature information, and finally inputs the fusion result into a trained deep neural network for target recognition. The neural network model training and recognition are very time-consuming, and its recognition efficiency will be affected

Images