Image Processing and Deep Learning Technology Help Power Equipment Intelligent Operation Inspection

Abstract

The new power system has the characteristics of “double height”, which mainly includes the introduction of wind power/photovoltaic and other power electronic devices on the basis of conventional power equipment, and the addition of typical converter valve hall internal converter transformer/valve tower/wall bushing/converter Bushing/super large voltage equalizing ball and other power equipment. For example, a large number of the power equipment need real-time operation and maintenance, it is urgent to develop efficient/practical/convenient intelligent operation and inspection technology for power equipment. Based on this, this paper combines image processing with deep learning technology, in which the image data includes high-definition digital photos/UV imager/infrared imager photos, and the deep learning algorithm mainly includes neural network and wavelet function processing. Through the above artificial intelligence algorithm processing, automatic extraction function of power equipment in image database and the comparative analysis function of historical image database are realized. Based on the above joint algorithm, it can effectively reduce the number of out detection of power equipment inspectors, automatically compare and analyze the massive image data acquisition and the historical image database, effectively discover the gradually strengthening points of UV discharge, the gradually increasing points of infrared imaging temperature or the gradually distorted points of displacement morphology, call high-definition digital photos based on the above information to mine the abnormal position of the state, and enlarge it to obtain the defect type. This paper attempts to provide the technical means for the intelligent operation inspection of the power equipment from the perspective of image processing. This technology has the broad application space and good theoretical research and engineering application value.