您目前所在的位置:首页 - 期刊简介 - 详细页面

铁道科学与工程学报

JOURNAL OF RAILWAY SCIENCE AND ENGINEERING

第11卷    第4期    总第60期    2014年8月

[PDF全文下载]    [Flash在线阅读]

    

文章编号:1672-7029(2014)04-0103-06
基于HMM在电机故障诊断上的研究
于天剑1,陈雅婷2,陈特放2,陈春阳1

(1.中南大学 交通运输学院,湖南 长沙 410075;
2.中南大学 信息科学与工程学院,湖南 长沙 410075
)

摘 要: 提出一种基于隐马尔可夫模型的方法用于故障的诊断与检测,该方法采用HMM与模式识别相结合的方法,通过对电机的电压电流信号进行特征提取和分析,构建电压电流空间模型,并且每个模型可以作为一级,每一级可以提高其判断的准确度,而HMM模型用做一个故障分类器来使用,相比于自适应模糊推理方法(MLFF)和多层前馈网络法(ANFIS),其准度有了很大提高,并且减少了计算。通过对不同故障诊断实例阐述了基于HMM的故障诊断方法的有效性和可行性。

 

关键字: 故障诊断;隐马尔可夫模型;感应电机;模式识别

Research on motor fault diagnosis based on HMM
YU Tianjian1, CHEN Yating2, CHEN Tefang2, CHEN Chunyang1

1. School of Traffic and Transportation Engineering, Central South University,Changsha 410075, China;
2. School of Information Science and Engineering, Central South University, Changsha 410075, China

Abstract:A method of hidden Markov based on Markov models was proposed in this paper for diagnosis and fault detection. Thereinto, the method combining HMM technique and pattern recognition feature can be utilized to extract and analyze the voltage and current signals of the motor, thereby constructing the voltage and the current space model. Moreover, each model can be regarded as a level which could improve the judging accuracy, while HMM model was used as a fault classifier, and in comparison with the adaptive fuzzy reasoning method (MLFF) and multilayer feed-forward network (ANFIS), its accuracy was improved greatly with less calculation number. Finally, the effectiveness of the method of fault diagnosis based on HMM and the feasibility were verified through the different fault diagnosis examples.

 

Key words: fault diagnosis; HMM model; induction motor; pattern recognition

ISSN 1672-7029
CN 43-1423/U

主管:中华人民共和国教育部 主办:中南大学 中国铁道学会 承办:中南大学
湘ICP备09001153号 版权所有:《铁道科学与工程学报》编辑部
------------------------------------------------------------------------------------------
地 址:湖南省长沙市韶山南路22号 邮编:410075
电 话:0731-82655133,82656174   传真:0731-82655133   电子邮箱:jrse@mail.csu.edu.cn