Atmospheric Corrosion State Evaluation Based on Surface Corrosion Morphology for Electrical Metal Frame Equipment in Chongqing Power Grid

This paper studies the atmospheric corrosion characteristics of grid metal frame equipment in Chongqing. Through the standard field test method of atmospheric corrosion -"exposure" method, this study carried out the substation site hanging test of the Q235 steel of the power transmission and transformation engineering structural material in the atmospheric environment, and mastered the corrosion data of Q235 steel in different corrosion stages. It was found that the morphology, quantity and characteristics of corrosion products on the metal surface varied greatly with the progress of corrosion. According to the metal corrosion morphology of different corrosion time, combined with image processing technology and wavelet transform algorithm, the parameters such as gray mean M, corrosion standard deviation σm, corrosion energy E, and energy percentage of wavelet image coefficient were selected as corrosion characteristic variable. At the same time, the BP neural network algorithm was used to qualitatively evaluate the corrosion state of the electrical equipment metal. By testing the on-site samples of the two substations, the corrosion state values of the samples were 0.946 and 0.8071, respectively, which is consistent with the actual corrosion degree, and the system had a good evaluation result.