基于VMD的自适应复合多尺度模糊熵及其在滚动轴承故障诊断中的应用

郑近德; 姜战伟; 代俊习; 潘紫微

doi:10.13224/j.cnki.jasp.2017.07.019

基于VMD的自适应复合多尺度模糊熵及其在滚动轴承故障诊断中的应用

doi: 10.13224/j.cnki.jasp.2017.07.019

安徽工业大学机械工程学院，安徽马鞍山 243032

基金项目: 国家自然科学基金（51505002）；安徽省高校自然科学研究重点资助项目（KJ2015A080）；安徽工业大学研究生创新研究基金(2016062)

计量
- 文章访问数: 812
- HTML浏览量: 0
- PDF量: 467
- 被引次数: 0
出版历程
- 收稿日期: 2016-10-19
- 刊出日期: 2017-07-28

VMD based adaptive composite multiscale fuzzy entropy and its application to fault diagnosis of rolling bearing

摘要

摘要: 提出了一种基于自适应多尺度模糊熵、ILS（迭代拉普拉斯得分）特征选择和粒子群优化支持向量机(PSO-SVM)的滚动轴承故障诊断方法。该方法采用变分模态分解对振动信号进行分解和重构，并计算重构信号的复合多尺度模糊熵；同时采用迭代拉普拉斯得分选择敏感故障特征，并将特征选择结果输入到基于粒子群优化支持向量机的多故障分类器进行识别。将提出的方法应用于滚动轴承试验数据分析。结果表明：该方法对试验数据的故障识别率为100%。并将基于ILS特征选择方法与基于SFS（sequential forward selection）特征选择进行了对比，表明基于SFS特征选择的最高识别率为92.86%，而基于ILS特征选择的故障识别率达到100%。
- 滚动轴承 /
- 故障诊断 /
- 多尺度模糊熵 /
- 变分模态分解 /
- 特征选择
Abstract: A rolling bearing fault diagnosis approach was proposed based on the adaptive multiscale fuzzy entropy, ILS (iterative Laplacian score) and PSO-SVM (particle swarm algorithm optimization support vector machine). In the proposed method, the variational mode decomposition was used for the decomposition and reconstruction. Then composite multiscale entropy fuzzy of the reconstructed signals was calculated. Besides, the iterative Laplacian score algorithm was used for the sensitive fault feature selection and the selected features were input to the PSO-SVM based classifier for training and recognition. Finally, the proposed method was applied to experiment data of rolling bearing. Results showed that the identifying rate of proposed method was 100%. Also, the ILS based feature selection was compared with the SFS (sequential forward selection) method; and the result indicated that the highest identifying fault rate of SFS based method was 92.86% while the identifying fault rate of the ILS based fault diagnosis method reached to 100%.
- rolling bearing /
- fault diagnosis /
- multiscale fuzzy entropy /
- variational mode decomposition /
- feature selection

HTML

参考文献(20)

[1]	王乐,张家忠,周成武,等.离心压缩机叶轮旋转失速的相空间重构及分形特征［J］.航空动力学报,2014,29(10):2424-2433.WANG Le,ZHANG Jiazhong,ZHOU Chengwu,et al.Phase space reconstruction and fractal characteristic of rotating stall in impeller of centrifugal compressor［J］.Journal of Aerospace Power,2014,29(10):2424-2433.(in Chinese)
[2]	张淑清,李盼,胡永涛,等.多重分形近似熵与减法FCM聚类的研究及应用［J］.振动与冲击,2015,34(18):205-209.ZHANG Shuqing,LI Pan,HU Yongtao,et al.Application of multifractal approximate entropy and subtractive FCM clustering in gearbox fault diagnosis［J］.Journal of Vibration and Shock,2015,34(18):205-209.(in Chinese)
[3]	PINCUS S M.Approximate entropy:a complexity measure for biological time series data［C］∥Proceedings of the IEEE Seventeenth Annual Northeast.Hartford,CT:IEEE,1991:35-36.
[4]	RICHMAN J S,MOORMAN J R.Physiological time-series analysis using approximate entropy and sample entropy［J］.American Journal of Physiology-Heart and Circulatory Physiology,2000,278(6):2039-2049.
[5]	CHEN W,WANG Z,XIE H,et al.Characterization of surface EMG signal based on fuzzy entropy［J］.IEEE Transactions on Neural Systems and Rehabilitation Engineering,2007,15(2):266-272.
[6]	CHEN W,ZHUANG J,YU W,et al.Measuring complexity using FuzzyEn,ApEn,and SampEn［J］.Medical Engineering and Physics,2009,31(1):61-68.
[7]	COSTA M,GOLDBERGER A L,PENG C K.Multiscale entropy analysis of biological signals［J］.Physical Review:E,2005,71(2):021906.1-021906.18.
[8]	COSTA M,GOLDBERGER A L,PENG C K.Multiscale entropy analysis of complex physiologic time series［J］.Physical Review Letters,2002,89(6):068102.1-068102.4.
[9]	COSTA M,PENG C K,GOLDBERGER A L,et al.Multiscale entropy analysis of human gait dynamics［J］.Physica A:Statistical Mechanics and Its Applications,2003,330(1):53-60.
[10]	WU S D,WU C W,LIN S G,et al.Time series analysis using composite multi-scale entropy［J］.Entropy,2013,15(3):1069-1084.
[11]	郑近德,潘海洋,程军圣,等.基于复合多尺度模糊熵的滚动轴承故障诊断方法［J］.振动与冲击,2016,35(8):116-123.ZHENG Jinde,PAN Haiyang,CHENG Junsheng,et al.Composite multiscale fuzzy entropy based rolling bearing fault diagnosis method［J］.Journal of Vibration and Shock,2016,35(8):116-123.(in Chinese)
[12]	DRAGOMIRETSKIY K,ZOSSO D.Variational mode decomposition［J］.IEEE Transactions on Signal Processing,2014,62(3):531-544.
[13]	姜战伟，郑近德，潘海洋，等.POVMD与包络阶次谱的变工况滚动轴承故障诊断［J］.振动、测试与诊断,2017,37(3):609-617.JIANG Zhanwei,ZHENG Jinde,PAN Haiyang,et al.Fault diagnosis under variable conditions based on parameter optimized variational mode decomposition and envelope order spectrum［J］.Journal of Vibration, Measurement and Diagnosis,2017,37(3):609-617.(in Chinese)
[14]	GARCA-NIETO P J, GARCA-GONZALO E, VILN J A V,et al. A new predictive model based on the PSO-optimized support vector machine approach for predicting the milling tool wear from milling runs experimental data[J].International Journal of Advanced Manufacturing Technology,2015,86(1):1-12.
[15]	HE X,CAI D,NIYOGI P.Laplacian score for feature selection［R］.Vancouver,Canada:Advances in Neural Information Processing Systems,2005.
[16]	BELKIN M,NIYOGI P.Laplacianeigenmaps for dimensionality reduction and data representation［J］.Neural Computation,2003,15(6):1373-1396.
[17]	NIYOGI X.Locality preserving projections［J］.Neural Information Processing Systems,2004,16(1):186-197.
[18]	ZHU L,MIAO L,ZHANG D.Iterative Laplacian score for feature selection［M］.Berilin:Springer,2012.
[19]	姜战伟，郑近德，潘海洋，等. 基于多尺度时不可逆与t-SNE流形学习的滚动轴承故障诊断[J].振动与冲击,2017,36(17):61-68.JIANG Zhanwei,ZHENG Jinde,PAN Haiyang,et al. Rolling bearing fault diagnosis method based on multiscale time irreversibility and t-SNE manifold learning[J].Journal of Vibration and Shock,2017,36(17):61-68.(in Chinese)
[20]	MARCANO-CEDENO A,QUINTANILLA-DOMNGUEZ J,Cortina-Januchs M G,et al.Feature selection using sequential forward selection and classification applying artificial metaplasticity neural network［C］∥Proceedings of 36th Annual Conference on IEEE Industrial Electronics Society.Glendale,AZ:IEEE,2010:2845-2850.