Intelligent fault detection of electrical equipment in ground substations using thermo vision technique

The aim of this paper is to detect the electrical equipment faults by making use of the moment method and statistical features of thermo images. Using the support vector machine (SVM) as a classifier and Zernike moment as image feature, a method for the intelligent detection of electrical equipment faults based on thermography has been introduced in this paper. By attention to the commonly occurring faults in the substations of distribution networks, two major faults occurring in ground substations low pressure panels that are related to the fuses have been chosen. The simulation results have been applied to the completely practical databases of real images of the distribution networks of North West of Tehran.