A Novel Fault Identification System in Substations Using Real Time Thermal Image Processing

Thermal Imaging has been an area of potential military interest in the last three decades and has been shrouded by veil of secrecy. Recently there has been resurgence of the interest in thermal imaging due to its use in non military applications such as biomedical engineering; conservation of natural resources, astronomy etc., and list of such applications is growing day by day. In this paper we focus at identifying the type of fault in the substation components before the actual fault to occur using thermal imaging camera. The substation components are captured using thermal imaging camera during working and still condition. The fault that to occur forehand is detected through naked eye by knowing the intensity of each color in the image captured. The image is processed through very large scale integration (VLSI) using field programmable gate array (FPGA) for enhancement of the image using various techniques such as image acquisition, preprocessing, segmentation, classification and decision making. The database is established to find the actual fault to occur for each and every temperature using the pixel calculated. This system eases of the time for analyzing the type of fault by providing the fault likely to occur for the desired temperature through the database and provides immediate solution for the fault.