汽轮发电机组故障诊断的模糊聚类分析新方法  

New Approach to Fuzzy Clustering Analysis in Multiple-faults Diagnosis of a Turbogenerator Set

作　　者：张彼德[1] 潘凌[1] 

机构地区：[1]西华大学电气信息学院,四川成都610039

出　　处：《西华大学学报（自然科学版）》2006年第3期8-10,共3页Journal of Xihua University:Natural Science Edition

摘　　要：已有的模糊聚类分析方法不能对汽轮发电机组振动多故障进行有效诊断。文章综合运用模糊聚类分析理论,将待检样本与所有标准故障样本一起作为分类样本,在模糊等价矩阵的传递闭包法的基础上,提出了一种适合汽轮发电机组振动多故障诊断的新方法。实例表明,该方法可有效诊断汽轮发电机组的振动多故障,具有良好的应用前景。This paper introduces a new method which can diagnose the vibration multiple-faults of a turbogenerator. The classified samples are composed of standard faulty samples and checked samples. This method, which is based on the transfer closure, can overcome the shortcoming that the traditional fuzzy clustering analysis can't effectively diagnose the multiple-faults of a turbogenerator. The experimental results indicate that the method in this paper is available and has a good foreground.

关 键 词：汽轮发电机组 振动多故障 模糊聚类 故障诊断 

分 类 号：TM311[电气工程—电机]