基于最小熵解卷积-变分模态分解和优化支持向量机的滚动轴承故障诊断方法

中国机械工程

基于最小熵解卷积-变分模态分解和优化支持向量机的滚动轴承故障诊断方法

姚成玉1;来博文1;陈东宁2，3;孙飞2,3;吕世君2,3

1.燕山大学河北省工业计算机控制工程重点实验室，秦皇岛，066004
2.燕山大学河北省重型机械流体动力传输与控制重点实验室，秦皇岛，066004
3.先进锻压成形技术与科学教育部重点实验室(燕山大学)，秦皇岛，066004

出版日期:2017-12-25 发布日期:2017-12-21
基金资助:
国家自然科学基金资助项目(51675460，51405426)；
河北省自然科学基金资助项目(E2016203306)；
中国博士后科学基金资助项目(2017M621101)
National Natural Science Foundation of China （No. 51675460，51405426）
Hebei Provincial Natural Science Foundation of China （No. E2016203306）
China Postdoctoral Science Foundation（No. 2017M621101）

Fault Diagnosis Method Based on MED-VMD and Optimized SVM for Rolling Bearings

YAO Chengyu1;LAI Bowen1;CHEN Dongning2,3;SUN Fei2,3;LYU Shijun2,3

1.Key Laboratory of Industrial Computer Control Engineering of Hebei Province,Yanshan University,Qinhuangdao,Hebei,066004
2.Hebei Provincial Key Laboratory of Heavy Machinery Fluid Power Transmission and Control,Yanshan University,Qinhuangdao，Hebei,066004
3.Key Laboratory of Advanced Forging & Stamping Technology and Science(Yanshan University),Ministry of Education of China,Qinhuangdao，Hebei,066004

Online:2017-12-25 Published:2017-12-21
Supported by:
National Natural Science Foundation of China （No. 51675460，51405426）
Hebei Provincial Natural Science Foundation of China （No. E2016203306）
China Postdoctoral Science Foundation（No. 2017M621101）

摘要/Abstract

摘要： 提出了一种基于最小熵解卷积和变分模态分解以及模糊近似熵的故障特征提取方法，并采用优化支持向量机对故障进行识别分类。首先利用最小熵解卷积方法降低噪声干扰并增强故障信号中故障特征信息，进而对降噪后的信号进行变分模态分解，并利用模糊近似熵量化变分模态分解后包含故障特征信息的模态分量以构建特征向量，之后通过采用扩展粒子群算法优化惩罚因子和核函数参数的支持向量机，对故障样本训练并完成故障识别分类。将所提方法应用于滚动轴承不同损伤程度、不同故障部位的实验数据，验证了该方法的有效性。与基于局部均值分解的特征提取方法相对比，结果表明所提方法可以更精确地提取出滚动轴承故障特征，并能够更准确地完成不同故障的识别；通过与基于网格寻优算法优化的支持向量机方法和基于扩展粒子群优化的最小二乘支持向量机方法相对比，结果表明所提方法具有更好的分类性能，能达到更好的诊断效果。

关键词: 故障诊断, 变分模态分解, 最小熵解卷积, 模糊近似熵, 支持向量机

Abstract: A method of fault feature extraction was proposed based on MED, VMD and fuzzy approximate entropy, and the optimized SVM was used to identify faults. The MED method was used to reduce the noise interferences and to enhance the fault feature informations in the fault signals, and the signals after noise reduction by VMD were decomposed, then, the fuzzy approximation entropy was used to quantify the modal components of fault feature informations after VMD, and the feature vectors were constructed, Finally, the extended particle swarm optimization(EPSO) algorithm was used to optimize the penalty factors and the kernel function parameters of SVM to complete the fault recognition classification. The proposed method was applied to the experimental data of rolling bearings, and the effectiveness of the method was verified. Compared with the feature extraction method based on local mean decomposition(LMD), it is shown that the proposed method may extract the features of rolling bearing faults more accurately and may identify different faults more accurately. Compared with SVM based on grid search algorithm and the least square support vector machines(LSSVM) based on EPSO algorithm, the proposed method has better classification performance and better diagnosis performance.

Key words: fault diagnosis, variational mode decomposition(VMD), minimum entropy deconvolution(MED), fuzzy approximate entropy, support vector machine(SVM)

中图分类号:

姚成玉1;来博文1;陈东宁2，3;孙飞2,3;吕世君2,3. 基于最小熵解卷积-变分模态分解和优化支持向量机的滚动轴承故障诊断方法[J]. 中国机械工程.

YAO Chengyu1;LAI Bowen1;CHEN Dongning2,3;SUN Fei2,3;LYU Shijun2,3. Fault Diagnosis Method Based on MED-VMD and Optimized SVM for Rolling Bearings[J]. China Mechanical Engineering.

参考文献

[1]罗颂荣,程军圣,杨宇.基于本征时间尺度分解和变量预测模型模式识别的机械故障诊断[J].振动与冲击,2013,32(13):43-48.
LUO Songrong. CHENG Junsheng, YANG Yu. Machine Fault Diagnosis Method Using ITD and Variable Predictive Model-based Class Discrimination[J]. Journal of Vibration and Shock, 2013, 32(13): 43-48.
[2]郑近德,潘海洋,戚晓利,等.复合层次模糊熵及其在滚动轴承故障诊断中的应用[J].中国机械工程,2016,27(15):2048-2055.
ZHENG Jinde, PAN Haiyang, QI Xiaoli, et al. Composite Hierarchical Fuzzy Entropy and Its Applications to Rolling Bearing Fault Diagnosis[J]. China Mechanical Engineering, 2016, 27(15): 2048-2055.
[3]BANERJEE S, MITRA M. Application of Cross Wavelet Transform for ECG Pattern Analysis and Classification[J]. IEEE Transactions on Instrumentation and Measurement, 2014, 63(2): 326-333.
[4]丁建明,王晗,林建辉,等.基于EMD-Hankel-SVD的高速列车万向轴动不平衡检测[J].振动与冲击,2015,34(9):164-170.
DING Jianming, WANG Han, LIN Jianhui, et al. Detection of Dynamic Imbalance Due to Cardan Shaft in High-speed Train Based on EMD-Hankel-SVD Method[J]. Journal of Vibration and Shock, 2015, 34(9): 164-170.
[5]卞家磊,朱春梅,蒋章雷,等.LMD-ICA联合降噪方法在滚动轴承故障诊断中的应用[J].中国机械工程,2016,27(7):904-910.
BIAN Jialei, ZHU Chunmei, JIANG Zhanglei, et al. Application of LMD-ICA to Fault Diagnosis of Rolling Bearings[J]. China Mechanical Engineering, 2016, 27(7): 904-910.
[6]DRAGOMIRETSKIY K, ZOSSO D. Variational Mode Decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544.
[7]王建国,吴林峰,秦绪华.基于自相关分析和LMD的滚动轴承振动信号故障特征提取[J].中国机械工程,2014,25(2):186-191.
WANG Jianguo, WU Linfeng, QIN Xuhua. Rolling Bearing Vibration Signal Fault Feature Extraction Based on Autocorrelation Analysis and LMD[J]. China Mechanical Engineering, 2014, 25(2): 186-191.
[8]臧怀刚,刘子豪,李玉奎.基于形态滤波和Laplace小波的轴承故障诊断[J].中国机械工程,2016,27(9):1198-1203.
ZANG Huaigang, LIU Zihao, LI Yukui. Fault Diagnosis of Bearings Based on Morphological Filter and Laplace Wavelet[J]. China Mechanical Engineering, 2016, 27(9): 1198-1203.
[9]KIM T, LEE K K. Estimation of Relative Recharge Sequence to Groundwater with Minimum Entropy Deconvolution[J]. Journal of Hydrology, 2005, 311: 8-19.
[10]HE D, WANG X, LI S, et al. Identification of Multiple Faults in Rotating Machinery Based on Minimum Entropy Deconvolution Combined with Spectral Kurtosis[J]. Mechanical Systems and Signal Processing, 2016, 81: 235-249.
[11]SAWALHI N, RANDALL R B, ENDO H. The Enhancement of Fault Detection and Diagnosis in Rolling Element Bearings Using Minimum Entropy Deconvolution Combined with Spectral Kurtosis[J]. Mechanical Systems and Signal Processing, 2007, 21(6): 2616-2633.
[12]龚廷恺,袁晓辉,王细洋.最小熵反褶积的数学形态法在滚动轴承故障特征提取中的应用[J].中国机械工程,2016,27(18):2467-2471.
GONG Tingkai, YUAN Xiaohui, WANG Xiyang. Applications of Mathematical Morphology Method to Fault Feature Extraction of Rolling Bearings Based on Minimum Entropy Deconvolution[J]. China Mechanical Engineering, 2016, 27(18): 2467-2471.
[13]BARSZCZ T, SAWALHI N. Fault Detection Enhancement in Rolling Element Bearings Using the Minimum Entropy Deconvolution[J]. Archives of Acoustics, 2012, 37(2): 131-141.
[14]GUO H, WANG W. An Active Learning-based SVM Multi-class Classification Model[J]. Pattern Recognition, 2015, 48(5): 1577-1597.
[15]万鹏, 王红军, 徐小力. 局部切空间排列和支持向量机的故障诊断模型[J]. 仪器仪表学报, 2012, 33(12): 2789-2795.
WAN Peng, WANG Hongjun, XU Xiaoli. Fault Diagnosis Model Based on Local Tangent Space Alignment and Support Vector Machine[J]. Chinese Journal of Scientific Instrument, 2012, 33(12): 2789-2795.
[16]张淑清,胡永涛,姜安琦,等.基于双树复小波和自适应权重和时间因子的粒子群优化支持向量机的轴承故障诊断[J].中国机械工程,2017,28(3):327-333.
ZHANG Shuqing, HU Yongtao, JANG Anqi, et al. Bearing Fault Diagnosis Based on DTCWT and AWTFPSO-optimized SVM[J]. China Mechanical Engineering, 2017, 28(3): 327-333.
[17]孟宗,李晶,龙海峰,等.基于压缩信息特征提取的滚动轴承故障诊断方法[J].中国机械工程,2017,28(7):806-812.
MENG Zong, LI Jing, LONG Haifeng, et al. Fault Diagnosis Method for Rolling Bearings Based on Compression Information Feature Extractions[J]. China Mechanical Engineering, 2017, 28(7): 806-812.
[18]莫思敏,曾建潮,谢丽萍.扩展的微粒群算法[J].控制理论与应用,2012,29(6):811-816.
MO Simin, ZENG Jianchao, XIE Liping. Extended Particle-swarm Optimization Algorithm[J]. Control Theory and Applications, 2012, 29(6): 811-816.
[19]YAO Chengyu, WANG Bin, CHEN Dongning. Reliability Optimization of Multi-State Hydraulic System Based on T-S Fault Tree and Extended PSO Algorithm[C]//Proceeding of the 6th IFAC Symposium on Mechatronic Systems(IFAC MECH2013). Hangzhou, 2013: 463-468.