基于局部均值分解与拉普拉斯特征映射的滚动轴承故障诊断方法

摘要/Abstract

摘要： 针对滚动轴承非平稳振动信号的特征提取及维数优化问题，提出了融合局部均值分解与拉普拉斯特征映射的轴承故障诊断方法。首先，通过局部均值分解对非平稳振动信号进行平稳化分解，提取乘积函数分量、瞬时频率及瞬时幅值的高维信号特征集；然后，将高维特征集作为拉普拉斯特征映射算法的学习对象，提取轴承高维故障特征集的内在流形分布，以获得敏感、稳定的轴承振动特征参数，实现基于非平稳振动信号分析的滚动轴承故障特征提取；最后，结合支持向量分类模型量化LMD-LE方法的特征提取效果，实现不同状况下的轴承故障分类。轴承故障样本分类识别平均正确率达到91.17%，表明LMD-LE方法有效实现了高维局部均值分解特征集合的降噪，所提取的特征矩阵对轴承故障特征描述准确。

关键词: 非平稳信号, 局部均值分解, 拉普拉斯特征映射, 故障诊断

Abstract: A new diagnosis method for feature extraction of non-stationary vibration signals and fault classification of rolling bearings was proposed based on LMD and LE. Firstly, the non-stationary vibration signals of rolling bearings were decomposed into several product functions with LMD. Then, dimensional fault feature sets were established by the time-frequency domain features of product function, instantaneous frequency and amplitude. Secondly, LE was introduced to extract the sensitive and stable characteristic parameters to describe the running states of rolling bearings effectively and accurately. Finally, support vector machine classification model was built to realize the classification of fault bearings. For test samples classification, the average prediction accuracy is as 91.17%.It means that the fusion method of the LMD and LE is suitable and feasible for the bearing fault feature extraction.

Key words: non-stationary signal, local mean decomposition(LMD), Laplacian eigenmap(LE), fault diagnosis

中图分类号:

TH17

徐倩倩, 刘凯, 侯和平, 徐卓飞. 基于局部均值分解与拉普拉斯特征映射的滚动轴承故障诊断方法[J]. 中国机械工程.

Xu Qianqian, Liu Kai, Hou Heping, Xu Zhuofei. Fault Diagnosis Method of Bearings Based on LMD and LE[J]. China Mechanical Engineering.

参考文献

[1]唐友福.基于广义局部频率的非线性非平稳信号故障特征提取方法研究[J].机械工程学报,2015,51(11):81-81.

Tang Youfu. Study on Fault Feature Extraction for Nonlinear Nonstationary Signals Based on General Local Frequency[J]. Journal of Mechanical Engineering, 2015, 51(11): 81-81.

[2]陈保家,何正嘉,陈雪峰，等.机车故障诊断的局域均值分解解调方法[J].西安交通大学学报,2010,44(5):40-44.

Chen Baojia, He Zhengjia, Cheng Xuefeng,et al. Locomotive Fault Diagnosis Based on Local Mean Decomposition Demodulating Approach [J]. Journal of Xian Jiaotong University, 2010,44(5):40-44.

[3]杨宇,王欢欢,程军圣，等.基于LMD的包络谱特征值在滚动轴承故障诊断中的应用[J].航空动力学报,2012,27(5):1153-1158.

Yang Yu, Wang Huanhuan, Cheng Junsheng, et al. Application of Envelope Spectrum Characteristics Based on LMD to Roller Bearing Fault Diagnosis[J].Journal of Aerospace Power,2012,27(5):1153-1158.

[4]侯蒙蒙,许同乐,高朋飞，等.基于LMD分解的风机轴承故障信号提取研究[J].中国农机化学报,2015,36(2):277-279.

Hou Mengmeng, Xu Tongle, Gao Pengfei, et al. Methods of Bearing Fault Characteristic Signal Extraction[J]. Journal of Chinese Agricultural Mechanization，2015,36(2):277-279.

[5]程军圣,杨怡,杨宇，等.基于LMD的能量算子解调机械故障诊断方法[J].振动、测试与诊断,2012,32(6):915-919.

Cheng Junsheng, Yang Yi, Yang Yu, et al. Mechanical Fault Diagnosis Method of Energy Operator Demodulating Approach Based on LMD[J].Journal of Vibration Measurement & Diagnosis,2012,32(6):915-919.

[6]王衍学,何正嘉,訾艳阳，等.基于LMD的时频分析方法及其机械故障诊断应用研究[J].振动与冲击,2012,31(9):9-12.

Wang Yanxue,He Zhengjia,Zi Yanyang, et al.Several Key Issues of Local Mean Decomposition Method Used in Mechanical Fault Diagnosis[J]. Journal of Vibration and Shock, 2012,31(9):9-12.

[7]黄浩,吕勇,肖涵，等.基于PCA和LMD分解的滚动轴承故障特征提取方法[J].仪表技术与传感器,2015(4):76-78.

Huang Hao, Lü Yong, Xiao Han, et al.Feature Extraction Method of Rolling Bearing Fault Based on Principal Component Analysis and Local Mean Decomposition[J]. Instrument Technique and Sensor, 2015(4):76-78.

[8]祝青林,吕勇,李宁，等.非局部均值去噪和LMD综合的滚动轴承故障诊断[J].机床与液压,2015,43(13):172-176.

Zhu Qinglin,Lü Yong, Li Ning, et al.Fault Diagnosis to Rolling Bearing by Integration of Nonlocal Means De-noising and LMD[J]. Machine Tool & Hydraulics, 2015,43(13):172-176.

[9]侯蒙蒙,许同乐.基于DT-LMD机床轴承故障信号提取研究[J].机床与液压,2015,43(7):185-188.

Hou Mengmeng, Xu Tongle. Study of Bearing Fault Signal Extraction of Machine Tool Based on DT-LMD[J]. Machine Tool & Hydraulics,2015,43(7):185-188.

[10]马朝永,刘茜,段建民，等.基于LMD与奇异值差分谱的滚动轴承故障诊断方法[J].北京工业大学学报,2014,40(2):182-188.

Ma Chaoyong, Liu Qian, Duan Jianmin, et al.Fault Diagnosis Method of Rolling Bearings Based on LMD and Singular Value Difference Spectrum[J]. Journal of Beijing University of Technology, 2014,40(2):182-188.

[11]冯研研,艾延廷,周海仑，等.改进形态滤波与LMD结合的滚动轴承故障诊断方法研究[J].机械设计与制造,2015(1): 83-86.

Feng Yanyan, Ai Yanting, Zhou Hailun,et al. Study on Improved Morphological Filter and LMD Fault Diagnosis of Roller Bearing[J]. Machinery Design & Manufacture, 2015(1):83-86.

[12]葛明涛,董素鸽.LMD及马氏距离敏感阈值的滚动轴承故障诊断[J].机械设计与制造,2015(2):210-213.

Ge Mingtao, Dong Suge. Fault Diagnosis Method of Rolling Bearings Based on LMD and Mahalanobis Distance Sensitive Threshold [J]. Machinery Design & Manufacture, 2015(2):210-213.

[13]程军圣,罗颂荣,杨斌，等.LMD能量矩和变量预测模型模式识别在轴承故障智能诊断中的应用[J].振动工程学报,2013,26(5):751-757.

Cheng Junsheng, Luo Songrong, Yang Bin, et al. LMD Energy Moment and Variable Predictive Model Based Class Discriminate and Their Application in Intelligent Fault Diagnosis of Roller Bearing [J]. Journal of Vibration Engineering,2013,26(5):751-757.

[14]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.

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.

[15]裴峻峰,于志远,董雪，等.基于LMD和灰色相似关联度的轴承故障诊断方法[J].机械设计与制造,2015(4):66-69.

Peng Junfeng, Yu Zhiyuan, Dong Xue, et al. Roller Bearing Fault Diagnosis Method Based on LMD and Grey Similar Incidence[J]. Machinery Design & Manufacture, 2015(4):66-69.

[16]贾茂林,王孙安,梁霖.利用非线性流形学习的轴承早期故障特征提取方法[J].西安交通大学学报,2010,44(5):45-49.

Jia Maolin, Wang Sunan, Liang Lin. Feature Extraction for Incipient Fault Diagnosis of Rolling Bearings Based on Non-linear Manifold Learning[J]. Journal of Xian Jiaotong University,2010,44(5):45-49.

[17]赵斐,陆宁云,杨毅，等.基于工况识别的注塑过程产品质量预测方法[J].化工学报,2013,64(7):2526-2534.

Zhao Fei, Lu Ningyun, Yang Yi, et al. Product Quality Prediction Method for Injection Molding Process Based on Operating Mode Recognition[J]. CIESC Jorunal,2013,64(7):2526-2534.

[18]刘海涛,汪增福,曹洋，等.基于流形学习的三维步态鲁棒识别方法[J].模式识别与人工智能,2011,24(4):464-472.

Liu Haitao, Wang Zengfu, Cao Yang, et al. 3D Robust Gait Recognition Based on Manifold Learning[J]. Pattern Recognition and Artificial Intelligence,2011,24(4):464-472.

[19]李月仙,韩振南,黄宏臣，等.基于拉普拉斯特征映射的旋转机械故障识别[J].振动与冲击,2014,33(18):21-25.

Li Yuexian, Han Zhennan, Huang Hongchen, et al. Fault Diagnosis of Rotating Machineries Based on Laplacian Eigenmaps[J].Journal of Vibration and Shock, 2014,33(18):21-25.

[20]He Qingbo. Vibration Signal Classification by Wavelet Packet Energy Flow Manifold Learning[J].Journal of Sound and Vibration,2013,332(7):1881-1894.

[21]He Qingbo. Time-frequency Manifold for Nonlinear Feature Extraction in Machinery Fault Diagnosis[J]. Mechanical Systems and Signal Processing,2013,35(1/2):200-218.

[22]李宏坤, 赵长生,周帅，等. 基于小波包-坐标变换的滚动轴承故障特征增强方法[J].机械工程学报, 2011,47(19):74-80.

Li Hongkun, Zhao Changsheng, Zhou Shuai, et al. Fault Feature Enhancement Method for Rolling Bearing Based on Wavelet Packet-coordinate Transformation[J].Journal of Mechanical Engineering, 2011,47(19):74-80.

[23]张媛,秦勇,邢宗义，等.基于LMD-PCA-LSSVM的滚动轴承安全域估计和状态辨识方法[J].振动与冲击,2013,32(20): 172-178.

Zhang Yuan, Qin Yong, Xing Zongyi, et al.Safety Region Estimation and State Identification of Rolling Bearings Based on LMD-PCA-LSSVM[J]. Journal of Vibration and Shock, 2013, 32(20):172-178.