摘要
针对变压器故障信息中存在有不完整、不确定及模糊性的知识,提出一种基于模糊逻辑和贝叶斯最优分类器结合的模糊贝叶斯分类器。该方法首先利用观察信息的模糊隶属度函数建立贝叶斯最优分类器中假设的后验概率,进而计算各类故障信息分类的结果并进行加权平均后得到最佳的诊断结果。应用和研究表明该方法能解决贝叶斯分类器中模糊信息获取的“瓶颈”难题,具有很强的学习能力,是一种有效的变压器绝缘故障诊断方法。
To deal with the incomplete,indeterminate and fuzzy fault information in transformer fault diagnosis, the paper proposes a novel transformer insulation fault diagnosis method called fuzzy Bayesian classifier based on fuzzy set and Bayesian optimal classifier. The method firstly applies fuzzy subjection degree funetion of the observed information to establish posterior probability of original assumption in Bayesian optimal classifier, the classified result based on each fault type is then calculated, and the best result is acquired after all these results are weighted average. Actual application shows that the proposed method can deal with the ＂bottle neck＂ of fuzzy knowledge acquisition in Bayesian optimal classifier,it possesses stronger learning abilities,and is an effectively transformer fault diagnosis method.
出处
《现代电子技术》
2007年第1期99-101,共3页
Modern Electronics Technique
关键词
贝叶斯最优分类器
模糊信息处理
变压器
故障诊断
Bayesian optimal classifier
fuzzy information processing, transformer
fault diagnosis
