基于精细复合多尺度熵和自编码的滚动轴承故障诊断方法
|
摘要
多尺度熵是一种有效衡量机械振动信号复杂度的非线性动力学方法。针对其存在的不足,引入精细复合多尺度熵(Refined composite multiscale entropy, RCMSE),在此基础上,结合自编码降维和遗传优化支持向量机,提出一种滚动轴承故障智能诊断新方法。首先,利用RCMSE提取滚动轴承振动信号多尺度复杂度特征,构建初始特征向量矩阵;其次,采用自编码对初始高维特征数据降维,得到低维流形特征;然后,将低维特征向量输入到基于遗传优化支持向量机的多故障模式分类器中进行训练、识别与诊断。最后,将所提方法应用于实验数据分析,并与多尺度熵方法进行对比,结果表明,该方法不仅能够有效诊断滚动轴承的工作状态和故障类型,而且识别率高于所对比方法。
Multi-scale entropy(MSE) is an effective nonlinear dynamics method for complexity measurement of mechanical vibration signals. Aiming at the insufficiency of MSE for shorter time series analysis, the refined composite multi-scale entropy(RCMSE) is introduced. By combining autoencoder for dimension reduction with genetic algorithm optimized support vector machine(GA-SVM), a new intelligent fault diagnosis method for rolling bearings is proposed.Firstly, the RCMSE is used to extract the multi-scale complexity characteristics of vibration signal and construct the initial fault feature matrix. Secondly, the autoencoder is used to reduce the dimension of the initial high-dimensional fault feature data to obtain the low-dimensional manifold features and realize the data visualization. Then, the low-dimensional features are input to the GA-SVM based multi-fault classifier for training, identifying and diagnosis. Finally, the proposed method is applied to the experimental data analysis and compared with the MSE based fault diagnosis method. The results show that the proposed method can effectively diagnose the working state and fault location of rolling bearings with a higher recognition rate than the MSE based fault diagnosis method.
Multi-scale entropy(MSE) is an effective nonlinear dynamics method for complexity measurement of mechanical vibration signals. Aiming at the insufficiency of MSE for shorter time series analysis, the refined composite multi-scale entropy(RCMSE) is introduced. By combining autoencoder for dimension reduction with genetic algorithm optimized support vector machine(GA-SVM), a new intelligent fault diagnosis method for rolling bearings is proposed.Firstly, the RCMSE is used to extract the multi-scale complexity characteristics of vibration signal and construct the initial fault feature matrix. Secondly, the autoencoder is used to reduce the dimension of the initial high-dimensional fault feature data to obtain the low-dimensional manifold features and realize the data visualization. Then, the low-dimensional features are input to the GA-SVM based multi-fault classifier for training, identifying and diagnosis. Finally, the proposed method is applied to the experimental data analysis and compared with the MSE based fault diagnosis method. The results show that the proposed method can effectively diagnose the working state and fault location of rolling bearings with a higher recognition rate than the MSE based fault diagnosis method.
引文
[1]刘永斌,龙潜,冯志华,等.一种非平稳、非线性振动信号检测方法的研究[J].振动与冲击,2007,26(12):131-134.
[2]邬再新,刘涛,黄成东.基于信息熵的涡旋压缩机振动信号分析[J].振动、测试与诊断,2014,34(1):168-172.
[3]刘义亚,李可,宿磊.基于近似熵和LCD-KELM的滚动轴承故障诊断[J].噪声与振动控制,2018,38(2):162:167.
[4]RICHMAN J S,MOORMAN J R.Physiological timeseries analysis using approximate entropy and sample entropy[J].Ajp Heart&Circulatory Physiology,2000,278(6):H2039-H2049.
[5]ZHANG L,LIU H,LIU H,et al.An intelligent fault diagnosis method based on multiscale entropy and SVMs[C].International Symposium on Neural Networks.Springer Berlin Heidelberg,2009:724-732.
[6]姜战伟,郑近德,潘海洋,等.基于改进多尺度熵与VPMCD的滚动轴承故障诊断[J].噪声与振动控制,2017,37(3):156-161.
[7]代俊习,郑近德,潘海洋,等.基于复合多尺度熵与拉普拉斯支持向量机的滚动轴承故障诊断方法[J].中国机械工程,2017,28(11):1339-1346.
[8]COSTA M,GOLDBERGER A L,PENG C K.Multiscale entropy analysis of biological signals[J].Physical Review E Statistical Nonlinear&Soft Matter Physics,2005,71(2 Pt 1):021906-021906.
[9]COSTA M D,PENG C K,GOLDBERGER A L.Multiscale analysis of heart rate dynamics:entropy and time irreversibility measures[J].Cardiovascular Engineering,2008,8(2):88-93.
[10]COSTA M,GOLDBERGER A L,PENG C K.Multiscale entropy analysis:a new measure of complexity loss in heart failure[J].Journal of Electrocardiology,2003,36(S1):39-40.
[11]COSTA M,HEALEY J A.Multiscale entropy analysis of complex heart rate dynamics:discrimination of age and heart failure effects[C].Computers in Cardiology.IEEE,2003:705-708.
[12]郑近德,程军圣,胡思宇.多尺度熵在转子故障诊断中的应用[J].振动振动、测试与诊断,2013,33(2):294-297.
[13]陈慧,张磊,熊国良,等.滚动轴承的MSE和PNN故障诊断方法[J].噪声与振动控制,2014,34(6):169-173.
[14]WU S D,WU C W,LIN S G,et al.Analysis of complex time series using refined composite multiscale entropy[J].Physics Letters A,2014,378(20):1369-1374.
[15]WADSTR?MER N,GUSTAFSSON D.Spectral dimensionality reduction using autoencoder[C].Swedish Symposium on Image Analysis,2016.
[16]WANG W,HUANG Y,WANG Y,et al.Generalized autoencoder:a neural network framework for dimensionality reduction[C].2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops,2014:496-503.
[17]SAKURADA M,YAIRI T.Anomaly detection using autoencoders with nonlinear dimensionality reduction[C].The Mlsda 2014,Workshop,2014:4-11.
[18]SCHITTENHELM R S,BORSDORF M,WANG Z,et al.Linear quadratic regulation of a rotating shaft being subject to gyroscopic effect using a genetic optimization algorithm[C].IAENG Transactions on Engineering Technologies,2014:183-195.
[19]POURBASHEER E,RIAHI S,GANJALI M R,et al.Application of genetic algorithm-support vector machine(GA-SVM)for prediction of BK-channels activity[J].European Journal of Medicinal Chemistry,2009,44(12):5023-5028.
[20]http://csegroups.case.edu/bearingdatacenter/pages/download-data-file[DB/OL].Bearing Data Center,Case Western Reserve University.
[21]THAPNGAM T,YU S,ZHOU W.DDoS discrimination by Linear Discriminant Analysis(LDA)[C].International Conference on Computing,Networking and Communications,IEEE,2012:532-536.
[2]邬再新,刘涛,黄成东.基于信息熵的涡旋压缩机振动信号分析[J].振动、测试与诊断,2014,34(1):168-172.
[3]刘义亚,李可,宿磊.基于近似熵和LCD-KELM的滚动轴承故障诊断[J].噪声与振动控制,2018,38(2):162:167.
[4]RICHMAN J S,MOORMAN J R.Physiological timeseries analysis using approximate entropy and sample entropy[J].Ajp Heart&Circulatory Physiology,2000,278(6):H2039-H2049.
[5]ZHANG L,LIU H,LIU H,et al.An intelligent fault diagnosis method based on multiscale entropy and SVMs[C].International Symposium on Neural Networks.Springer Berlin Heidelberg,2009:724-732.
[6]姜战伟,郑近德,潘海洋,等.基于改进多尺度熵与VPMCD的滚动轴承故障诊断[J].噪声与振动控制,2017,37(3):156-161.
[7]代俊习,郑近德,潘海洋,等.基于复合多尺度熵与拉普拉斯支持向量机的滚动轴承故障诊断方法[J].中国机械工程,2017,28(11):1339-1346.
[8]COSTA M,GOLDBERGER A L,PENG C K.Multiscale entropy analysis of biological signals[J].Physical Review E Statistical Nonlinear&Soft Matter Physics,2005,71(2 Pt 1):021906-021906.
[9]COSTA M D,PENG C K,GOLDBERGER A L.Multiscale analysis of heart rate dynamics:entropy and time irreversibility measures[J].Cardiovascular Engineering,2008,8(2):88-93.
[10]COSTA M,GOLDBERGER A L,PENG C K.Multiscale entropy analysis:a new measure of complexity loss in heart failure[J].Journal of Electrocardiology,2003,36(S1):39-40.
[11]COSTA M,HEALEY J A.Multiscale entropy analysis of complex heart rate dynamics:discrimination of age and heart failure effects[C].Computers in Cardiology.IEEE,2003:705-708.
[12]郑近德,程军圣,胡思宇.多尺度熵在转子故障诊断中的应用[J].振动振动、测试与诊断,2013,33(2):294-297.
[13]陈慧,张磊,熊国良,等.滚动轴承的MSE和PNN故障诊断方法[J].噪声与振动控制,2014,34(6):169-173.
[14]WU S D,WU C W,LIN S G,et al.Analysis of complex time series using refined composite multiscale entropy[J].Physics Letters A,2014,378(20):1369-1374.
[15]WADSTR?MER N,GUSTAFSSON D.Spectral dimensionality reduction using autoencoder[C].Swedish Symposium on Image Analysis,2016.
[16]WANG W,HUANG Y,WANG Y,et al.Generalized autoencoder:a neural network framework for dimensionality reduction[C].2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops,2014:496-503.
[17]SAKURADA M,YAIRI T.Anomaly detection using autoencoders with nonlinear dimensionality reduction[C].The Mlsda 2014,Workshop,2014:4-11.
[18]SCHITTENHELM R S,BORSDORF M,WANG Z,et al.Linear quadratic regulation of a rotating shaft being subject to gyroscopic effect using a genetic optimization algorithm[C].IAENG Transactions on Engineering Technologies,2014:183-195.
[19]POURBASHEER E,RIAHI S,GANJALI M R,et al.Application of genetic algorithm-support vector machine(GA-SVM)for prediction of BK-channels activity[J].European Journal of Medicinal Chemistry,2009,44(12):5023-5028.
[20]http://csegroups.case.edu/bearingdatacenter/pages/download-data-file[DB/OL].Bearing Data Center,Case Western Reserve University.
[21]THAPNGAM T,YU S,ZHOU W.DDoS discrimination by Linear Discriminant Analysis(LDA)[C].International Conference on Computing,Networking and Communications,IEEE,2012:532-536.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |