Research of Power Transformer Fault Diagnosis System Based on Rough Sets and Bayesian Networks
As one of the most important electric equipment for reliable power supply, the secure operation of power transformer must be guaranteed. Three-ratio method based on the Dissolved Gases Analysis (DGA) is most widely used for transformer fault diagnosis currently. Its advantage is simple and easy to use, but its encoding is incomplete and the faults classification zone is over absolute. This paper combines rough sets and Bayesian Network. Rough sets is used to get useful characters, simplify data sets, obtain simplification rules and the minimum property sets; Bayesian Network is used to analyze the faults caused by uncertain elements in complex system. The fault diagnostic model is built by Bayesian Network Tool (BNT) in MATLAB, and the simulation result shows the validity of this method.
Jun Hu and Qi Luo
Q. Li et al., "Research of Power Transformer Fault Diagnosis System Based on Rough Sets and Bayesian Networks", Advanced Materials Research, Vol. 320, pp. 524-529, 2011