基于粗糙集、模糊集和贝叶斯最优分类器的变压器绝缘故障诊断与维护模型研究.pdf

th Proceedings of the 25 Chinese Control Conference 7-11 August, 2006, Harbin, Heilongjiang 730070 E-mail: shsen@163.com : : , , A Decision Model for Transformer Fault Diagnosis and Maintenance Based on Rough Set and Fuzzy Set and Bayesian Optimal Classifier Hongsheng Su School of Information and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070 E-mail: shsen@163.com Abstract: Based on Bayesian optimal classifier, combining with rough set and fuzzy set, a new transformer fault diagnosis and maintenance mode is presented in the paper. In this method fuzzy membership function of the observed information are used to establish posterior probability of primary assumptions in Bayesian optimal classifier, the classified result based on each fault information is for that worked out, the optimal diagnosis result is acquired after all these results are weighted average. Then based on rough model of Bayesian risk decision, the diagnosis results of all fault information are identified to constitute possible maintenance strategies. Actual application shows that the proposed method can deal with the “bottle neck” of fuzzy knowledge acquisition in Bayesian optimal classifier and possesses stronger learning abilities, and is an effective transformer fault diagnosis and maintenance method. Key Words: Bayesian optimal classifier, fuzzy information processing, rough set, fault diagnosis 1 (Introduction)