Fuzzy logic based automatic diagnosis of power apparatus by infrared imaging

This paper describes a thermographic application system for the electrical power industry. The infrared imager has a range from 40 degrees C to 950 degrees C and maximum resolution down to 0.01 degrees C. A new algorithm for image matching has been devised to match slightly different infrared images of the same object by adaptively adjusting the five parameters, namely x- and y- translation, rotation, x- and y- scaling respectively. The diagnosis is automatically executed by a fuzzy logic-based expert system which extracts the major features within the thermograms and recommends appropriate actions for maintenance.<<ETX>>