An Approach to the Transformer Faults Diagnosing Based on Rough Set and Artificial Immune System

Abstract

Aiming at the shortages of the diagnosing efficiency, applicability and knowledge acquisition ability in traditional transformer fault diagnosing methods, an immune model for diagnosing transformer fault is established in this paper by combining the strong ability of recognition and learning in the artificial immune system (AIS) with the attributes' objectively reduction of the rough set theory (RST) together. The optimal coding of the antibodies and the antigents based on RST, the algorithm in the immune model for diagnosing and learning is analyzed in detail. Finally, the experimental results confirmed that this model has high diagnosis accuracy, strong robustness and good learning ability.