Bearing Fault Diagnosis Method with Information Entropy and Ensemble Kurtosis Optimized VMD and PSO-SVM
-
摘要: 为了解决变分模态分解参数人为确定的问题,并能够实现轴承故障的精确诊断,构建了一种信息熵和合成峭度优化的变分模态分解(VMD)和粒子群算法优化支持向量机(PSO-SVM)的轴承故障诊断方法。该方法首先运用合成峭度倒数与信息熵乘积的最小值原则对VMD参数进行优化,再由优化的参数对原始故障信号进行变分模态分解,得到既定的若干本征模态分量(IMFs),再选取信息熵与合成峭度倒数的乘积最小的IMF作为最佳IMF,再对其提取故障特征构成特征向量,输入PSO-SVM进行故障分类。最后,运用仿真信号和实际轴承数据验证了本文方法的有效性。Abstract: To solve the problem of artificial determination of variational modal decomposition parameters and to achieve accurate diagnosis of bearing faults, a new bearing fault diagnosis method based on the variational modal decomposition (VMD) which is optimized with information entropy and ensemble kurtosis, and particle swarm optimized support vector machine(PSO-SVM) is constructed in this study. In this method, optimize the VMD parameters by using the principle of minimum of product of the reciprocal of ensemble kurtosis and the information entropy; decompose the original fault signal by the above optimized VMD and obtain some established intrinsic mode functions (IMFs); select the IMF with the minimum product of the information entropy and the reciprocal of ensemble kurtosis as the best IMF, and extract its fault features to form the feature vector and input PSO-SVM to classify the fault type. Both simulation signal and the actual bearing data are applied to verify the effectiveness of proposed method.
-
表 1 各IMF综合评价指标l
IMF IMF1 IMF2 IMF3 IMF4 IMF5 l 1.35 1.10 1.25 1.26 0.84 表 2 本文方法和EMD+PSO-SVM在2∶3比例下的分类识别结果
轴承状态(标签) 样本次序 EMD+PSO-SVM 本文方法 错误样本个数/个 正确率/% 错误样本个数/个 正确率/% 正常(1) 1~20 0 100 0 100 内圈轻微故障(2) 21~40 0 100 0 100 内圈中度故障(3) 41~60 2 90 0 100 内圈严重故障(4) 61~80 0 100 2 90 外圈轻微故障(5) 81~100 2 90 1 95 外圈严重故障(6) 101~120 4 80 0 100 总计统计 1~120 8 88.9 3 95.8 表 3 不同方法在不同比例下参数c和g的值
比例 本文方法 EMD+PSO-SVM c g c g 1∶1 6.56 34.19 5.75 0.97 2∶3 4.329 30.829 27.06 95.47 -
[1] 丁承君, 张良, 冯玉伯, 等. VMD和t-SNE相结合的滚动轴承故障诊断[J]. 机械科学与技术, 2020, 39(5): 758-764 doi: 10.13433/j.cnki.1003-8728.20190193DING C J, ZHANG L, FENG Y B, et al. Fault diagnosis method of rolling bearing combining VMD with t-SNE[J]. Mechanical Science and Technology for Aerospace Engineering, 2020, 39(5): 758-764 (in Chinese) doi: 10.13433/j.cnki.1003-8728.20190193 [2] HUANG N E, SHEN Z, LONG S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 1998, 454(1971): 903-995 doi: 10.1098/rspa.1998.0193 [3] SMITH J S. The local mean decomposition and its applica-tion to EEG perception data[J]. Journal of the Royal Society Interface, 2005, 2(5): 443-54 doi: 10.1098/rsif.2005.0058 [4] WU Z H, HUANG N E. Ensemble empirical mode decomposi-tion: a noise-assisted data analysis method[J]. Advances in Adaptive Data Analysis, 2009, 1(1): 1-41 doi: 10.1142/S1793536909000047 [5] LEI Y G, HE Z J, ZI Y Y. EEMD method and WNN for fault diagnosis of locomotive roller bearings[J]. Expert Systems with Applications, 2011, 38(6): 7334-7341 doi: 10.1016/j.eswa.2010.12.095 [6] DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544 doi: 10.1109/TSP.2013.2288675 [7] 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/OL].自动化学报, (2019-08-12)[2020-03-20].https://doi.org/10.16383/j.aas.190345LIU J C, QUAN H, YU X, et al. Rolling bearing fault diagnosis based on parameter optimization VMD and sample entropy[J/OL]. Acta Automatica Sinica, (2019-08-12)[2020-03-20]. https://doi.org/10.16383/j.aas.190345 (in Chinese) [8] LI Z P, CHEN J L, ZI Y Y, et al. Independence-oriented VMD to identify fault feature for wheel set bearing fault diagnosis of high speed locomotive[J]. Mechanical Systems and Signal Processing, 2017, 85: 512-529 doi: 10.1016/j.ymssp.2016.08.042 [9] WANG Z P, JIA L M, QIN Y. Adaptive diagnosis for rotating machineries using information geometrical kernel-ELM based on VMD-SVD[J]. Entropy, 2018, 20(1): 73-91 doi: 10.3390/e20010073 [10] 李华, 伍星, 刘韬, 等. 基于信息熵优化变分模态分解的滚动轴承故障特征提取[J]. 振动与冲击, 2018, 37(23): 219-225 https://www.cnki.com.cn/Article/CJFDTOTAL-ZDCJ201823031.htmLI H, WU X, LIU T, et al. Bearing fault feature extraction based on VMD optimized with information entropy[J]. Journal of Vibration and Shock, 2018, 37(23): 219-225 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZDCJ201823031.htm [11] MIAO Y H, ZHAO M, LIN J. Identification of mechanical compound-fault based on the improved parameter-adaptive variational mode decomposition[J]. ISA Transactions, 2019, 84: 82-95 doi: 10.1016/j.isatra.2018.10.008 [12] ZHANG X Y, LIANG Y T, ZHONG J Z, et al. A novel bearing fault diagnosis model integrated permutation entropy, ensemble empirical mode decomposition and optimized SVM[J]. Measurement, 2015, 69: 164-179 doi: 10.1016/j.measurement.2015.03.017 [13] 张小龙, 张氢, 秦仙蓉, 等. 基于ITD复杂度和PSO-SVM的滚动轴承故障诊断[J]. 振动与冲击, 2016, 35(24): 102-107, 138 https://www.cnki.com.cn/Article/CJFDTOTAL-ZDCJ201624017.htmZHANG X L, ZHANG Q, QIN X R, et al. Rolling bearing fault diagnosis based on ITD Lempel-Ziv complexity and PSO-SVM[J]. Journal of Vibration and Shock, 2016, 35(24): 102-107, 138 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZDCJ201624017.htm [14] 唐贵基, 王晓龙. 变分模态分解方法及其在滚动轴承早期故障诊断中的应用[J]. 振动工程学报, 2016, 29(4): 638-648 https://www.cnki.com.cn/Article/CJFDTOTAL-ZDGC201604011.htmTANG G J, WANG X L. Variational mode decomposition method and its application on incipient fault diagnosis of rolling bearing[J]. Journal of Vibration Engineering, 2016, 29(4): 638-648 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZDGC201604011.htm [15] LIU T, CHEN J, DONG G M, et al. The fault detection and diagnosis in rolling element bearings using frequency band entropy[J]. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 2013, 227(1): 87-99 doi: 10.1177/0954406212441886