基于内禀模态奇异值分解和支持向量机的故障诊断方法

被引:35
作者
程军圣
于德介
杨宇
机构
[1] 湖南大学机械与汽车工程学院
[2] 湖南大学机械与汽车工程学院 长沙
关键词
旋转机械; 故障诊断; 经验模态分解; 内禀模态函数; 奇异值分解; 支持向量机;
D O I
10.16383/j.aas.2006.03.023
中图分类号
TH17 [机械运行与维修];
学科分类号
摘要
提出了一种基于内禀模态(Intrinsic mode functions,简称IMFs)奇异值分解和支持向量机(Support vector machine,简称SVM)的故障诊断方法.采用经验模态分解(Empirical mode decomposition,简称EMD)方法对旋转机械故障振动信号进行分解,将得到的若干个内禀模态分量自动形成初始特征向量矩阵,然后对该矩阵进行奇异值分解,提取其奇异值作为故障特征向量,并进一步根据支持向量机分类器的输出结果来判断旋转机械的工作状态和故障类型.对齿轮振动信号的分析结果表明,即使在小样本情况下,基于内禀模态奇异值分解和支持向量机的故障诊断方法仍能有效地识别齿轮的工作状态和故障类型.
引用
收藏
页码:475 / 480
页数:6
相关论文
共 8 条
  • [1] An overview of statistical learning theory. Vapnik V N. IEEE Transactions on Neural Networks . 1999
  • [2] Matrix Theory and Its Application. Jiang Z X,Shi G L. . 1988
  • [3] Introduction to statistical learning theory and support vector machines. Zhang X G. Acta Automatica Sinica . 2000
  • [4] Helicopter gearbox fault detection: A neural network based approach. Dellomo M R. Journal of Vibration and Acoustics . 1999
  • [5] A new view of nonlinear water waves: The Hilbert spectrum. Huang N E,Shen Z,Long S R. Annual Review of Fluid Mechanics . 1999
  • [6] Artificial neural network based fault diagnosis of rotating machinery using wavelet transforms as processor. Paya B A,Esat I I,Badi M N M. Journal of Mechanical Systems . 1997
  • [7] The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Huang N E,Shen Z,Long S R. Proceedings of the Royal Society of London, A . 1998
  • [8] Characterizing nonstationary wind speed using empirical mode decomposition. Xu Y L,Chen J. Journal of Structural Engineering . 2004