Rolling Bearing Fault Diagnosis Research Combined Parameter Optimization VMD with OMPE
-
摘要: 针对难以判别的轴承运行振动信号中的状态特征, 提出参数优化变分模态分解(VMD)和最优多尺度排列熵(OMPE)结合的特征向量构建的方法, 采用支持向量机(SVM)进行故障诊断。VMD的分解结果由分解个数和惩罚因子限制, 采用量子粒子群算法(QPSO)优化达到分解的最优效果。考虑轴承运行的周期性质, 提出基于轴承故障运行周期特性的最优多尺度排列熵概念, 运用模态分量与最优尺度排列熵结合构建特征向量。通过不同方法采用支持向量机识别对比分析, 表明上述提出的方法能有效提取特征, 提高轴承的故障诊断的精度。Abstract: Aiming at the state features in the vibration signal of rolling bearing operation which are difficult to distinguish, a method of constructing feature vectors combined with parameter optimization variational modal decomposition (VMD) and optimal multi-scale permutation entropy (OMPE) is proposed, and support vector machine (SVM) is next used to diagnose faults. The decomposition result of VMD is limited by the number of decompositions and the penalty factor, and the quantum particle swarm optimization (QPSO) is used to achieve the optimal effect of decomposition. Considering the periodic nature of bearing operation, the concept of optimal multi-scale permutation entropy based on the period characteristics of bearing fault operation is proposed, and the feature vector is constructed by combining modal components and optimal-scale permutation entropy. Using support vector machine identification and comparative analysis through different methods shows that the proposed method can effectively extract features and improve the accuracy of rolling bearing fault diagnosis.
-
表 1 不同K值下所对应的中心频率
K 中心频率/Hz 3 525 2 113 2 981 - - - - 4 507 1 134 2 245 2 984 - - - 5 505 1 130 2 137 2 818 3 037 - - 6 503 1 125 2 075 2 365 2 847 3 042 - 7 492 1 002 1 199 2 185 2 760 2 975 3 114 表 2 不同α值下对应的中心频率
α 中心频率/Hz 500 504 1 130 2 171 2 752 2 974 3 114 1 000 504 1 130 2 171 2 752 2 974 3 113 1 500 504 1 130 2 171 2 751 2 974 3 113 2 000 503 1 125 2 075 2 365 2 847 3 042 2 500 503 1 125 2 075 2 365 2 847 3 042 3 000 503 1 125 2 075 2 365 2 847 3 042 表 3 参数组合在[6, 2 000]时的包络熵值
n 1 2 3 4 5 6 Ep 6.797 6 6.521 9 6.651 7 6.517 2 6.445 0 6.570 4 表 4 采用VMD-PE方法构建的特征向量
标签 特征值1 特征值2 特征值3 特征值4 1 1.108 9 1.372 2 1.673 2 1.713 2 2 1.213 3 1.357 2 1.499 6 1.619 0 3 1.110 8 1.344 6 1.580 2 1.644 3 4 0.930 2 1.277 5 1.583 5 1.716 8 -
[1] 陈强强, 戴邵武, 戴洪德, 等. 基于IMF特征提取的滚动轴承故障诊断[J]. 噪声与振动控制, 2020, 40(1): 46-50 https://www.cnki.com.cn/Article/CJFDTOTAL-ZSZK202001010.htmCHEN Q Q, DAI S W, DAI H D, et al. Fault diagnosis of rolling bearings based on IMF feature extraction[J]. Noise and Vibration Control, 2020, 40(1): 46-50 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZSZK202001010.htm [2] 王金东, 代梅, 夏法锋, 等. 基于EMD信息熵和支持向量机的往复压缩机轴承故障诊断[J]. 流体机械, 2014, 42(7): 43-46 doi: 10.3969/j.issn.1005-0329.2014.07.010WANG J D, DAI M, XIA F F, et al. Fault diagnosis for reciprocating compressor bearings based on EMD-information entropy and SVM[J]. Fluid Machinery, 2014, 42(7): 43-46 (in Chinese) doi: 10.3969/j.issn.1005-0329.2014.07.010 [3] 孙国栋, 王俊豪, 徐昀, 等. CEEMD-WVD多尺度时频图像的滚动轴承故障诊断[J]. 机械科学与技术, 2020, 39(5): 688-694 doi: 10.13433/j.cnki.1003-8728.20190192SUN G D, WANG J H, XU Y, et al. CEEMD-WVD multi-scale time-frequency image of rolling bearing fault diagnosis[J]. Mechanical Science and Technology for Aerospace Engineering, 2020, 39(5): 688-694 (in Chinese) doi: 10.13433/j.cnki.1003-8728.20190192 [4] 任学平, 李攀, 王朝阁. 基于LMD和MCKD的滚动轴承早期故障诊断[J]. 现代制造工程, 2018(9): 143-147, 160 https://www.cnki.com.cn/Article/CJFDTOTAL-XXGY201809027.htmREN X P, LI P, WANG C G. Early fault diagnosis for rolling bearing based on LMD and MCKD[J]. Modern Manufacturing Engineering, 2018(9): 143-147, 160 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-XXGY201809027.htm [5] DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544 doi: 10.1109/TSP.2013.2288675 [6] 刘建昌, 权贺, 于霞, 等. 基于参数优化VMD和样本熵的滚动轴承故障诊断[J]. 自动化学报, 2020, 48(3): 808-819 https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO202203013.htmLIU J C, QUAN H, YU X, et al. Rolling bearing fault diagnosis based on parameter optimization VMD and sample entropy[J]. Acta Automatica Sinica, 2020, 48(3): 808-819 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO202203013.htm [7] 李宏坤, 侯梦凡, 唐道龙, 等. 基于POVMD和CAF的低转速齿轮箱故障诊断[J]. 振动、测试与诊断, 2020, 40(1): 35-42, 201 https://www.cnki.com.cn/Article/CJFDTOTAL-ZDCS202001006.htmLI H K, HOU M F, TANG D L, et al. Low speed gearbox fault diagnosis based on POVMD and CAF[J]. Journal of Vibration, Measurement & Diagnosis, 2020, 40(1): 35-42, 201 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZDCS202001006.htm [8] 边杰. 基于遗传算法参数优化的变分模态分解结合1.5维谱的轴承故障诊断[J]. 推进技术, 2017, 38(7): 1618-1624 https://www.cnki.com.cn/Article/CJFDTOTAL-TJJS201707024.htmBIAN J. Fault diagnosis of bearing combining parameter optimized variational mode decomposition based on genetic algorithm with 1.5-dimensional spectrum[J]. Journal of Propulsion Technology, 2017, 38(7): 1618-1624 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-TJJS201707024.htm [9] 马洪斌, 佟庆彬, 张亚男. 优化参数的变分模态分解在滚动轴承故障诊断中的应用[J]. 中国机械工程, 2018, 29(4): 390-397 doi: 10.3969/j.issn.1004-132X.2018.04.003MA H B, TONG Q B, ZHANG Y N. Applications of optimization parameters VMD to fault diagnosis of rolling bearings[J]. China Mechanical Engineering, 2018, 29(4): 390-397 (in Chinese) doi: 10.3969/j.issn.1004-132X.2018.04.003 [10] LI Y J, ZHANG W H, XIONG Q, et al. A rolling bearing fault diagnosis strategy based on improved multiscale permutation entropy and least squares SVM[J]. Journal of Mechanical Science and Technology, 2017, 31(6): 2711-2722 doi: 10.1007/s12206-017-0514-5 [11] 戴洪德, 陈强强, 戴邵武, 等. 基于平滑先验分析和排列熵的滚动轴承故障诊断[J]. 推进技术, 2020, 41(8): 1841-1849 https://www.cnki.com.cn/Article/CJFDTOTAL-TJJS202008019.htmDAI H D, CHEN Q Q, DAI S W, et al. Rolling bearing fault diagnosis based on smoothness priors approach and permutation entropy[J]. Propulsion Technology, 2020, 41(8): 1841-1849 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-TJJS202008019.htm [12] 宁琦, 耿读艳, 王晨旭, 等. 基于多尺度排列熵及PSO-SVM的输电线路故障判别[J]. 电子测量与仪器学报, 2019, 33(7): 173-180 https://www.cnki.com.cn/Article/CJFDTOTAL-DZIY201907024.htmNING Q, GENG D Y, WANG C X, et al. Fault identification of EHV transmission lines based on multi-scale entropy and PSO-SVM[J]. Journal of Electronic Measurement and Instrumentation, 2019, 33(7): 173-180 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-DZIY201907024.htm [13] SUN J, FENG B, XU W B. Particle swarm optimization with particles having quantum behavior[C]//Proceedings of the 2004 Congress on Evolutionary Computation. Portland, OR, USA: IEEE, 2004: 326-331 [14] 唐贵基, 王晓龙. 参数优化变分模态分解方法在滚动轴承早期故障诊断中的应用[J]. 西安交通大学学报, 2015, 49(5): 73-81 https://www.cnki.com.cn/Article/CJFDTOTAL-XAJT201505012.htmTANG G J, WANG X L. Parameter optimized variational mode decomposition method with application to incipient fault diagnosis of rolling bearing[J]. Journal of Xi'an Jiaotong University, 2015, 49(5): 73-81 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-XAJT201505012.htm [15] 张建财, 高军伟. 基于变分模态分解和多尺度排列熵的滚动轴承故障诊断[J]. 噪声与振动控制, 2019, 39(6): 181-186 https://www.cnki.com.cn/Article/CJFDTOTAL-ZSZK201906033.htmZHANG J C, GAO J W. Fault diagnosis of train rolling bearings based on variational modal decomposition and multi-scale permutation entropy[J]. Noise and Vibration Control, 2019, 39(6): 181-186 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZSZK201906033.htm [16] 陈鹏, 赵小强, 朱奇先. 基于多尺度排列熵和改进多分类相关向量机的滚动轴承故障诊断方法[J]. 电子测量与仪器学报, 2020, 34(2): 20-28 https://www.cnki.com.cn/Article/CJFDTOTAL-DZIY202002003.htmCHEN P, ZHAO X Q, ZHU Q X. Rolling bearing fault diagnosis method based on multi-scale permutation entropy and improved multi-class relevance vector machine[J]. Journal of Electronic Measurement and Instrumentation, 2020, 34(2): 20-28 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-DZIY202002003.htm