Pollution Degree Detection of Insulators based on Hyperspectral Imaging Technology

Abstract

Present researches prove that the pollution flashover of operating insulators still threatens the safe and reliable operation of power system. However, traditional detection methods are difficult to achieve noncontact detection. The hyperspectral imaging technology is a nondestructive testing technology which combines image information and spectral information, therefore it has potential to become an important detection method for power device external insulation. In order to study the application of hyperspectral imaging technology in the detection of insulator pollution degree, a new data processing method is produced. On the one hand, the result of spectral processing shows that there are corresponding relationships between the pollution degree and the reflectivity value, the reflectivity waveform and base material. On the other hand, the result of image processing proves that it can distinguish between the polluted and nonpolluted areas by using principal components analysis and K-means clustering algorithm. The above parts prove that the application of hyperspectral imaging technology in the detection of insulator’s external insulation is feasible and it will have a broad application prospect.