期刊文献+

基于无限隐Markov模型的旋转机械故障诊断方法研究 被引量:10

Research on rotating machinery fault diagnosis method based on infinite hidden Markov model
在线阅读 下载PDF
导出
摘要 针对传统隐Markov模型(HMM)在机械故障诊断中存在的不足,即HMM过学习或溢出问题以及隐状态数需要事先假定,提出了基于无限隐马尔可夫模型(i HMM)的机械故障诊断方法。在提出的方法中,以谱峭度为特征提取,i HMM为识别器,并以最大似然估计来确定设备运转中出现的故障类型。同时,将提出的方法与传统的HMM故障识别方法进行了对比分析。实验结果表明,提出的方法是有效的,得到了非常满意的识别效果。提出的方法能够有效避免了HMM在建模初期遗留下的不足,可以自适应确定模型中隐藏状态数和模型数学结构,因此,提出的方法明显优于HMM故障识别方法。 Aimingat the deficiency of traditional HMMfault recognition model in machinery fault diagnosis,i.e.over-learning or overflow problems and requiring to assume the hidden states in advance,a new machinery fault diagnosismethod based on infinite Hidden Markov Model (iHMM)is proposed.In the proposed method,the spectral kurtosis is used as the fault feature extraction,the iHMM as theidentifier,and the maximum likelihood estimation is used to determinethe mechanical fault type occurred in the equipment operation. At the same time,the proposed method and traditional HMMfault identification method are compared and analyzed.The experiment result shows that the proposedrecognition method has very satisfactory recognition effect.The proposed method can effectively avoid the deficiency of the HMMmethod in the initial modeling stage,can adaptively determine the number of hidden states in the model and the mathematical structure of the model.Therefore,the proposed method is obviously superior to the traditional HMMfault recognition method.
出处 《仪器仪表学报》 EI CAS CSCD 北大核心 2016年第10期2185-2192,共8页 Chinese Journal of Scientific Instrument
基金 国家自然科学基金(51675258 51265039 51261024) 机械传动国家重点实验室开放基金(SKLMT-KFKT-201514) 广东省数字信号与图像处理技术重点实验室(2014GDDSIPL-01)项目资助
关键词 无限隐马尔可夫模型 故障诊断 谱峭度 最大似然估计 模式识别 fault diagnosis spectral kurtosis maximum likelihood estimation pattern recognition
作者简介 李志农(通讯作者),2003年于浙江大学获得博士学位,现为南昌航空大学教授,主要研究方向为智能检测与信号处理、机械状态监测与故障诊断。E-mail:lizhinong@tsinghua.org.cn柳宝,2013年在湖北工程学院获得学士学位,现为南昌航空大学硕士研究生,主要研究方向为智能检测与信号处理、机械状态监测与故障诊断。E-mail:albert_bao@foxmail.com侯娟,2014年在山西大学获得学士学位,现为南昌航空大学硕士研究生,主要研究方向为智能检测与信号处理,机械状态监测与故障诊断。E-mail:cathera@foxmail.com
  • 相关文献

参考文献16

  • 1李志农,蒋静,冯辅周,袁振伟.基于量子粒子群优化Volterra时域核辨识的隐Markov模型识别方法[J].仪器仪表学报,2011,32(12):2693-2698. 被引量:12
  • 2LI ZH N, HAN J, SUN JJ, et al. Fault recognition method based on independent component analysis and hidden Markov model [ J 1. Journal of Vibration and Control, 2007, 13(2) : 125-137.
  • 3李志农,郝伟,韩捷,褚福磊,吴昭同.基于非线性时序模型盲辨识的因子隐Markov模型识别方法[J].机械工程学报,2007,43(1):191-195. 被引量:3
  • 4BOUTROS T, LIANG M. Detection and diagnosis of bearing and cutting tool faults using hidden Markov models [ J]. Mechanical Systems and Signal Processing, 2011, 25(6): 2102-2124.
  • 5LI ZH N, HE YY, CHU FL, et at. Fault recognition method for speed-up and speed-down process of rotating machinery based on independent component analysis and factorial hidden Markov model [ J ]. Journal of Sound and Vibration, 2006, 291 (1-2) : 60-71.
  • 6LI ZH N, WU ZH T, HE YY, et at. Hidden Markov model based fault diagnostics method in speed-up and speed-down process for rotating machinery [ J ]. Mechanical System and Signal Processing, 2005, 19(2) : 329 -339.
  • 7GERAMIFARD O, XU JX, PANDA SK. Fauh detection and diagnosis in synchronous motors using hidden Markov model-based semi-nonparametric approach [ J ]. Engineering Applications of Artificial Intelligence, 2013, 26(8) : 1919-1929.
  • 8GEORGOULAS G, MUSTAFA MO, TSOUMAS IP, et al. Principal component analysis of the start-up transient and Hidden Markov modeling for broken rotor bar fauh diagnosis in asynchronous machines [ J ]. Expert Systems with Applications, 2013, 40 (17) : 7024-7033.
  • 9BOUTROS T, LIANG M. Detection and diagnosis of bearing and cutting tool faults using hidden Markov models [J]. Mechanical Systems and Signal Processing, 2011, 25(6): 2102-2124.
  • 10LI ZH N, WU G H, JIANG J, et al. Factorial hidden Markov model recognition method based on multi - channel information fusion [ J ]. Advanced Materials Research, 2011, 291-294 : 2027-2033.

二级参考文献20

  • 1魏瑞轩,吴寿林,王希圣.一类非线性系统的故障诊断与实现[J].仪器仪表学报,2004,25(z1):804-805. 被引量:3
  • 2李志农,何永勇,褚福磊,吴昭同.用于机械故障诊断的门限自回归模型盲辨识[J].清华大学学报(自然科学版),2005,45(8):1036-1039. 被引量:3
  • 3李志农,郝伟,韩捷,褚福磊,吴昭同.基于非线性时序模型盲辨识的因子隐Markov模型识别方法[J].机械工程学报,2007,43(1):191-195. 被引量:3
  • 4徐敏,须文波.基于量子粒子群算法的复杂函数参数估计[J].计算机工程与设计,2007,28(15):3665-3667. 被引量:4
  • 5GHAHRAMANI Z,JORDAN M I. Factorial hidden Markov models [ J ]. Machine Learning, 1997, 29 (2-3) : 245 -273.
  • 6LI Z N, HE Y Y, CHU F L, et al. Fault recognition method for speed-up and speed-down process of rotating machinery based on independent component analysis and factorial hidden Markov model [ J ]. Journal of Sound and Vibration, 2006, 291( 1-2): 60-71.
  • 7RABINER L R. A tutorial on hidden Markov models and selected applications in speech recognition [ J ].Proceed- ings of IEEE, 1989, 77(2) : 257-285.
  • 8LI Z N, HAN J, SUN J J, et al. Fault recognition meth- od based on independent component analysis and hidden Markov model [ J ]. Journal of Vibration and Control, 2007, 13(2): 125-137.
  • 9KARIM A M,QIU WZ,HUA Y B.Blind system identification[J].Proceedings of the IEEE,1998,8(8):1 310-1 322.
  • 10GHAHRAMANI Z,JORDAN M.Factorial hidden Markov models[J].Machine Learning,1997,29(3):245-275.

共引文献19

同被引文献101

引证文献10

二级引证文献26

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部