Perception based insulator recognition and defect diagnosis method

Abstract

The invention discloses a perception based insulator recognition and defect diagnosis method. The method comprise the following steps: step (1), an electric transmission line knowledge model is adopted for perceiving multiple parallel line structures of an insulator; step (2), an area where the insulator is located is recognized, an overlapped output area is detected as follows: an overlapped area is combined, and a potential insulator area is corrected to a rectangle in any angle; and step (3), insulator chip-missing defect diagnosis based on blocking characteristic quantity is performed, and the glass insulator self-destruction chip-missing defect is diagnosed by adopting two steps of insulator area blocking and interblock similarity computation. The perception based insulator recognition and defect diagnosis method has the benefits that influence of background on recognition of the insulator area can be effectively precluded, and the accurate rate of insulator defect recognition is greatly improved.

Description

technical field [0001] The invention relates to a perception-based insulator identification and defect diagnosis method, which is mainly used in the field of defect diagnosis of high-voltage transmission lines. Background technique [0002] At present, the research on the complex artificial object recognition and defect diagnosis of high-voltage lines has just started, and there are few published literatures. Relevant research focuses on the development of equipment such as line inspection robots, helicopters, and unmanned aerial vehicle inspection technology, while the identification and defect diagnosis of high-voltage lines are mainly based on the significant image features of high-voltage lines, such as the identification and defect diagnosis of main parts of wires and insulators . [0003] Due to the long-term erosion of insulators in the field environment, many faults usually occur. According to the respective characteristics of glass, porcelain and synthetic insulato...

AI Technical Summary

Problems solved by technology

[0005] Chinese patent (patent name: a method for automatic recognition of infrared images of insulator strings, application number: 201310098598.8) proposes a method for automatic recognition of insulators based on the boundaries of infrared images, but this method uses SIFT features on the template image and the image to be detected Matching for automatic identification of insulator strings, realizing the positioning of the insulator string area, and does not involve the diagnosis of insulator defects

[0006] Chinese patent (patent name: texture-based insulator defect diagnosis method, application number: 201110303911.8) proposes a defect diagnosis method through GLCM and Gabor filter, and the positioning of the insulator is mainly realized by the prior knowledge of the insulator connection equipment. The positioning effect on insulator strings is poor, which affects the efficiency of insulator defect positioning

Images