Research on transformer fault diagnosis method and calculation model by using fuzzy data fusion in multi-sensor detection system

Abstract

In order to achieve the failure of unattended power network equipment, this paper proposes a new transformer fault diagnosis method by using multi band infrared imager sensor and discharge circuit detection sensor to set up the eight sensors detection platform. Analyzes the transformer fuzzy fault characteristics, designs the detection platform of transformer fault diagnosis, establishes a transformer fuzzy fault diagnosis model with the exponential trust function of the photoelectric sensor, the average weighted consistency of each photoelectric sensor and the support degree of the photoelectric sensors, gives the data fusion method with the trust function of the sensor and the maximum model value. Through experiment and analysis, this fault diagnosis model can improve the fusion precision and diagnostic accuracy more effectively than the general fusion algorithm and arithmetic mean value algorithm, and can scientifically diagnose the transformer equipment of power grid from multi angle. Thereby, the feasibility and effectiveness of the method are verified.