Gas discrimination method for detecting transformer faults by neural network

This paper describes a method available for early detection of abnormality in an oil‐filled transformer. In this method, four gas sensors having different characteristics and neural network are used to identify gas species (H2, CH4, C2H4, C2H2 and mixture of two species). To improve the selectivity of gas sensors, the time response patterns induced by changing sensor temperature and the stationary sensor output are identified by neural network. Furthermore, the mixture ratio of gases is derived by using the stationary sensor output in response to the changing sensor temperature. Gas species are well discriminated, and the mixture ratio derived from the sensor output agrees well with the measurement by gas chromatography. Therefore, it is confirmed that our method is applicable to the transformer diagnostic technology.