Title :
Gas discrimination method for detecting transformer faults by neural network
Author :
Nogami, Takeki ; Yokoi, Yoshihide ; Ichiba, Hideo ; Atsumi, Yoshihiro
Author_Institution :
Shikoku Res. Inst. Inc., Takamatsu, Japan
fDate :
27 Jun- 2 Jul 1994
Abstract :
A method available for early detection of abnormality in an oil-filled transformer is described, in which four gas sensors having different characteristics and neural network are used to identify gas species (H2, CH4, C2H4, C 2H2 and mixture of two species). In order to improve the selectivity of gas sensors, the time response patterns induced by changing sensor temperature, and the stationary sensor output is 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 sensor output agrees well with the measurement by gas chromatography. Therefore, it is confirmed that our method is applicable to the transformer diagnostic technology
Keywords :
fault diagnosis; gas sensors; neural nets; power engineering computing; power transformer testing; H2; abnormality detection; gas chromatography; gas discrimination method; gas mixture ratio; gas sensors; neural network; oil-filled transformer; sensor temperature; stationary sensor output; time response patterns; transformer fault detection; Fault detection; Gas chromatography; Gas detectors; Gases; Neural networks; Oil insulation; Power transformer insulation; Sensor phenomena and characterization; Temperature sensors; Voltage;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374816
