Rotating Machinery Fault Diagnosis Based on Local Mean Decomposition and Hidden Markov Model

Abstract

Abstract:

Based on LMD and HMM, a new method for rotating machinery fault diagnosis was proposed. The method was applied to rolling bearing fault diagnosis. First of all, fault signals were decomposed by LMD, the instantaneous energy distribution of each signal was extracted to form the fault feature vectors, and then input the feature vectors into the HMM classifier for malfunction recognition, the maximum likelihood probability which was output by HMM classifier was in the fault state. A practical fault signal of a rolling bearing with corrosive pitting was applied to test the method. Experimental results show that the method of LMD-HMM is superior to the method of empirical mode decomposition(EMD)-HMM and can identify the rolling bearing faults accurately and effectively.

Key words: fault diagnosis, rotating machinery, local mean decomposition(LMD), hidden Markov model(HMM)

摘要：

提出了基于局部均值分解（LMD）和隐马尔科夫模型(HMM)的旋转机械故障诊断方法。首先，对故障信号进行局部均值分解，提取瞬时能量作为故障特征向量；然后将故障特征向量输入HMM分类器进行模式识别，输出各状态的似然概率；以最大似然概率所对应的故障状态为诊断结果。通过滚动轴承点蚀故障诊断试验验证了该方法的有效性，并将其与基于EMD-HMM的故障诊断方法进行了比较。结果表明，基于LMD-HMM的故障诊断方法更适用于旋转机械的故障诊断。

关键词: 故障诊断, 旋转机械, 局部均值分解, 隐马尔科夫模型

CLC Number:

Meng Zong, Yan Xiaoli, Wang Yachao. Rotating Machinery Fault Diagnosis Based on Local Mean Decomposition and Hidden Markov Model[J]. China Mechanical Engineering, 2014, 25(21): 2942-2946,2951.

孟宗, 闫晓丽, 王亚超. 基于LMD和HMM的旋转机械故障诊断[J]. 中国机械工程, 2014, 25(21): 2942-2946,2951.

References

[1]钟秉林，黄仁. 机械故障诊断学[M]. 北京: 机械工业出版社，2007.
[2]Huang N E，Shen Z, Long S R，et al. The Empirical Mode Decomposition and the Hilbert Spectrum for Nonlinear and Non-stationary Time Series Analysis[J]. Proceeding of Royal Society London，1998，454(1971)：903-995.
[3]程军圣，于德介，杨宇. 基于EMD和分形维数的转子系统故障诊断[J]. 中国机械工程，2005，16(12)：1088-1091.
Cheng Junsheng，Yu Dejie，YangYu. Fault Diagnosis for Rotor System Based on EMD and Fractal Dimension[J]. China Mechanical Engineering，2005，16(12)：1088-1091.
[4]李志农，何永勇，褚福磊. 基于Wigner高阶谱的机械故障诊断的研究[J]. 机械工程学报，2005，41(4)：119-122.
Li Zhinong，He yongyong，Chu Fulei. Machine Fault Diagnosis Base on Wigner-Ville High Order Sepctra[J]. Chinese Journal of Mechanical Engineering，2005, 41(4)：119-122.
[5]孟宗，李姗姗. 基于小波半软阈值和EMD的旋转机械故障诊断[J]. 中国机械工程，2013，24(10)：1279-1283.
Meng Zong，Li Shanshan. Research on Fault Diagnosis for Rotating Machinery Basedon Semi-soft Wavelet Threshold and EMD[J]. China Mechanical Engineering，2013，24(10)：1279-1283.
[6]赵志宏，杨绍普，李韶华. 基于Hilbert谱奇异值的轴承故障诊断[J]. 中国机械工程，2013，24(3)：346-350.
Zhao Zhihong，Yang Shaopu，Li Shaohua，Bearing Fault Diagnosis Based on Hilbert Spectrum and Singular Value Decomposition[J]. China Mechanical Engineering，2013，24(3)：346-350.
[7]李强，王太勇，王正英，等. 基于EMD和支持向量机数据描述的故障智能诊断[J]. 中国机械工程，2008，19(22)：2718-2721.
Li Qiang，Wang Taiyong，Wang Zhengying，et al. Intelligent Fault Diagnosis Based on Empirical Mode Decomposition and Support Vector Data Description[J]. China Mechanical Engineering，2008，19(22)：2718-2721.
[8]刘小峰，秦树人，柏林. 基于小波包的经验模态分解法的研究及应用[J]. 中国机械工程，2007，18(10)：1201-1204.
Liu Xiaofeng，Qin Shuren，Bo Lin. Wavelet Packet Analysis-based Empirical Mode Decomposition and Its Application[J]. China Mechanical Engineering，2007，18(10)：1201-1204.
[9]张俊红，李林洁，马文朋，等. EMD-ICA联合降噪在滚动轴承故障诊断中的应用[J]. 中国机械工程，2013，24(11)：1468-1472.
Zhang Junhong，Li Linjie，Ma Wenpeng，et al. Application of EMD-ICA to Fault Diagnosis of Rolling Bearings[J]. China Mechanical Engineering，2013，24(11)：1468-1472.
[10]Smith J S. The Local Mean Decomposition and Its Application to EEG Perception Data[J]. Journal of the Royal Society Interface，2005，2(5)：443-454.
[11]程军圣，张亢，杨宇. 局部均值分解方法及其在滚动轴承故障诊断中的应用[J]. 中国机械工程，2009，20(22)：2711-2717.
Cheng Junsheng，Zhang Kang，Yang Yu. Local Mean Decomposition and Its Application to Roller Bearing Fault Diagnosis[J]. China Mechanical Engineering，2009，20(22)：2711-2717.
[12]张亢，程军圣，杨宇. 基于局部均值分解的阶次跟踪分析及其在齿轮故障诊断中的应用[J]. 中国机械工程，2011，22(14):1732-1736.
Zhang Kang，Cheng Junsheng，Yang Yu. Order Tracting Analysis Based on Local Mean Decomposition and Its Applications to Gear Fault Diagnosis[J]. China Mechanical Engineering，2011，22(14)：1732-1736.
[13]陶新民，徐晶，杜宝祥. 基于小波域隐马尔可夫模型故障诊断方法[J]. 振动与冲击，2009，28(4)：33-37.
Tao Xinmin，Xu Jing，Du Baoxiang. Bearing Fault Diagnosis Using a Wavelet-doma in Hidden Markov Model[J]. Journal of Vibration and Shock，2009，28(4)：33-37.
[14]吴军，邵新宇，邓超. 隐马尔科夫链模型在装备运行可靠性预测中的应用[J]. 中国机械工程，2010，21(19)：2345-2349.
Wu Jun，Shao Xinyu，Deng Chao. A HMC-based Equipment Operation Reliability Prediction with Multiple Observation Sequences[J]. China Mechanical Engineering，2010，21(19)：2345-2349.
[15]曹冲锋，杨世锡，杨将新. 一种基于瞬时能量分布特征的汽轮发电机组转子故障诊断新方法[J]. 振动与冲击，2009，28(3)：35-39.
Cao Chongfeng，Yang Shixi，Yang Jiangxin. A New Fault Diagnosis Method for a Rotor of a Steam Turbine Generator Set Based on Instantaneous Energy Distribution Characteristics[J]. Journal of Vibration and Shock，2009，28(3)：35-39.