期刊文献+

基于HMM的导航设备故障状态识别模型研究

下载PDF
导出
摘要 针对导航设备结构复杂,故障发生频繁,故障类型难判断的特点,本文提出了基于状态维修(CBM)的隐马尔可夫模型(HMM)故障状态识别方法。首先通过灵敏度分析法确定导航设备的电路中发生变化最明显的元件,通过改变元件参数来设置电路的不同故障状态;其次对采集到的工作状态数据进行线性判别分析(LDA),并建立导航设备故障状态识别模型;最后对导航设备故障进行状态识别。结果表明,本文提出的方法能够对导航设备电路不同故障状态进行状态识别,状态识别率可以达到94%。
出处 《电子世界》 2015年第19期192-194,共3页 Electronics World
  • 相关文献

参考文献3

二级参考文献39

  • 1DuanChendong HeZhengjia JiangHongkai.NEW METHOD FOR WEAK FAULT FEATURE EXTRACTION BASED ON SECOND GENERATION WAVELET TRANSFORM AND ITS APPLICATION[J].Chinese Journal of Mechanical Engineering,2004,17(4):543-547. 被引量:12
  • 2王仲生,何红,陈钱.小波分析在发动机早期故障识别中的应用研究[J].西北工业大学学报,2006,24(1):68-71. 被引量:18
  • 3MING D, HE D. A segmental hidden semi-Markov model (HSMM)-based diagnostics and prognostics frame work and methodology [ J ]. Mechanical System and Signal Pro- cessing, 2007, 21: 2248-2266.
  • 4ROMBERG J K, CHOI H, BARANIUK R G. Bayesian tree- structured image modeling using Wavelet-domain hidden Markov models [ J ]. IEEE Transactions on Image Processing, 2001, 10(7): 1056-106.
  • 5VIRK S M, MUHAMMAD A, MARTINEZ-ENRIQUZE A M. Fault prediction using artificial neural network and fuzzy logic [ J ]. The 7th Mexican International Confer- ence on Artificial Intelligence, 2008( 1 ) : 149-154.
  • 6PONCI F, CRISTALDI L, FAIFER M, et al. Innovative approach to early fault detection for induction motors. IEEE international symposium on diagnostics for electric machine[J]. Power Electronics and Drivers, 2007 (6) : 283 -288.
  • 7DUONG N Q K, VINCENT E, GRIBUNVAL R. spatial covariance models for underdetermined reverberant audio source separation [ C ]. Proc WASPAA, New York, 2009 : 129-132.
  • 8LOPEZ L D, PECHT M G. Modeling of IC socket con- tacts reisitance for reliability and health monitoring [ C ]. IEEE Transactions on Relibility, 2009(2) :264-270.
  • 9PENG Z K, JACKSON M R, RONGONG J A, et al. On the energy leakage of discrete wavelet transform [ J ]. Me- chanical System and Signal Processing, 2009,23 ( 2 ) : 330-343.
  • 10SUNW, PALAZOGLU A, ROMAGNOLI J A. Detecting abnormal process trends by wavelet-domain hidden Mark- ov models [ J ]. Journal of the American Institute of Chemical Engineers, 2003,49 (1) : 140-150.

共引文献35

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