Rolling Bearing Fault Diagnosis with Parameters Optimized VMD and SVM
-
摘要: 为了便于选取变分模态分解(VMD)参数、综合考虑轴承故障信号周期冲击性、循环平稳性, 各分量与原信号相关性及不同故障诊断的问题, 构建了一种天牛须搜索算法(BAS)优化VMD及加权合成峭度提取最优本征模态函数(IMF), 并结合布谷鸟算法优化支持向量机(CS-SVM)的轴承故障诊断方法。先以平均包络熵为BAS的适应度函数优化VMD参数, 接着对信号进行VMD分解。然后以加权合成峭度最大优选IMF, 对所选IMF提取故障特征并组成特征向量。最后, 将其输入CS-SVM中进行故障分类。运用仿真信号和实际轴承数据验证所提方法的可行性。Abstract: In order to properly select the parameters of variational mode decomposition (VMD), and to overall consider the periodic impulsiveness and cyclostationary of bearing fault signal, the correlation between each component and the original signal, and the diagnosis problem of different faults, a new bearing fault diagnosis method using beetle antennae search (BAS) optimized VMD and weighted ensemble kurtosis for extracting the optimal intrinsic mode function (IMF) combining with the cuckoo search algorithm optimized support vector machine (CS-SVM) is constructed in this study. Firstly, BAS is used to optimize VMD parameters with the mean envelope entropy as the fitness function, and optimized VMD is used to decompose signal. Then, IMF is optimized by the maximum value of weighted ensemble kurtosis, and extract its fault features to form feature vectors. Finally, they are imported into the CS-SVM for fault classification. Simulation signal and actual bearing data are used to verify the proposed method.
-
表 1 IMFs加权合成峭度值
IMF1 IMF2 IMF3 IMF4 0.610 5 0.695 4 1.021 0 0.704 8 表 2 IMFs加权合成峭度值
IMFi EKCI IMFi EKCI IMF1 0.942 1 IMF5 0.930 8 IMF2 1.085 8 IMF6 0.877 5 IMF3 1.277 4 IMF7 0.749 6 IMF4 1.257 2 表 3 轴承7种故障状态样本
状态 数据标签 损伤直径/mm 训练集 测试集 正常 1 - 12 18 内圈故障1 2 0.18 12 18 内圈故障2 3 0.36 12 18 内圈故障3 4 0.53 12 18 滚动体故障 5 0.18 12 18 外圈故障1 6 0.18 12 18 外圈故障2 7 0.53 12 18 总和 - - 84 126 表 4 不同分类算法比较
分类器 Tm/s C g 识别率/% CS-SVM 25.142 91.163 1.071 99.2 PSO-SVM 29.123 0.492 8 211.313 98.4 AFSA-SVM 49.941 29.957 164.771 98.4 -
[1] 杜小磊, 陈志刚, 王衍学. 基于同步挤压S变换和集成深层脊波自编码器的轴承故障诊断[J]. 振动与冲击, 2020, 39(14): 59-68 https://www.cnki.com.cn/Article/CJFDTOTAL-ZDCJ202014009.htmDU X L, CHEN Z G, WANG Y X. Bearing fault diagnosis based on the synchrosqueezed S transform and ensemble deep ridgelet auto-encoder[J]. Journal of Vibration and Shock, 2020, 39(14): 59-68 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZDCJ202014009.htm [2] 刘敏, 范红波, 张英堂, 等. 机械振动信号自适应多尺度非线性动力学特征提取方法研究[J]. 振动与冲击, 2020, 39(14): 224-232+250 doi: 10.13465/j.cnki.jvs.2020.14.031LIU M, FAN H B, ZHANG Y T, et al. Adaptive multi-scale method for the non-linear dynamic feature extraction of mechanical vibration signals[J]. Journal of Vibration and Shock, 2020, 39(14): 224-232+250 (in Chinese) doi: 10.13465/j.cnki.jvs.2020.14.031 [3] 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 [4] SMITH J S. The local mean decomposition and its application to EEG perception data[J]. Journal of the Royal Society Interface, 2005, 2(5): 443-454 doi: 10.1098/rsif.2005.0058 [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] 张俊, 张建群, 钟敏, 等. 基于PSO-VMD-MCKD方法的风机轴承微弱故障诊断[J]. 振动、测试与诊断, 2020, 40(2): 287-296+418 https://www.cnki.com.cn/Article/CJFDTOTAL-ZDCS202002011.htmZHANG J, ZHANG J Q, ZHONG M, et al. PSO-VMD-MCKD based fault diagnosis for incipient damage in wind turbine rolling bearing[J]. Journal of Vibration, Measurement & Diagnosis, 2020, 40(2): 287-296+418 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZDCS202002011.htm [7] YANG K, WANG G F, DONG Y, et al. Early chatter identification based on an optimized variational mode decomposition[J]. Mechanical Systems and Signal Processing, 2019, 115: 238-254 doi: 10.1016/j.ymssp.2018.05.052 [8] 王向阳, 何岭松, 王平江, 等. 基于VMD的铣刀破损检测[J]. 振动与冲击, 2020, 39(16): 135-140+162 https://www.cnki.com.cn/Article/CJFDTOTAL-ZDCJ202016019.htmWANG X Y, HE L S, WANG P J, et al. Milling cutter breakage detection based on VMD[J]. Journal of Vibration and Shock, 2020, 39(16): 135-140+162 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZDCJ202016019.htm [9] GAI J B, SHEN J X, HU Y F, et al. An integrated method based on hybrid grey wolf optimizer improved variational mode decomposition and deep neural network for fault diagnosis of rolling bearing[J]. Measurement, 2020, 162, 107901 doi: 10.1016/j.measurement.2020.107901 [10] SIVAVARAPRASAD G, SREE PADMAJA R, VENKATA RATNAM D. Mitigation of ionospheric scintillation effects on GNSS signals using variational mode decomposition[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(3): 389-393 doi: 10.1109/LGRS.2016.2644723 [11] 郑小霞, 周国旺, 任浩翰, 等. 基于变分模态分解和排列熵的滚动轴承故障诊断[J]. 振动与冲击, 2017, 36(22): 22-28 https://www.cnki.com.cn/Article/CJFDTOTAL-ZDCJ201722004.htmZHENG X X, ZHOU G W, REN H H, et al. A rolling bearing fault diagnosis method based on variational mode decomposition and permutation entropy[J]. Journal of Vibration and Shock, 2017, 36(22): 22-28 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZDCJ201722004.htm [12] 焦博隆, 钟志贤, 刘翊馨, 等. 基于蝙蝠算法优化的变分模态分解的转子裂纹检测方法[J]. 振动与冲击, 2020, 39(6): 98-103+124 https://www.cnki.com.cn/Article/CJFDTOTAL-ZDCJ202006014.htmJIAO B L, ZHONG Z X, LIU Y X, et al. Rotor crack detection method based on variational mode decomposition based on optimization parameters of bat algorithm[J]. Journal of Vibration and Shock, 2020, 39(6): 98-103+124 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZDCJ202006014.htm [13] JIANG X Y, LI S. BAS: beetle antennae search algorithm for optimization problems[J]. International Journal of Robotics and Control, 2018, 1(1): 1-5 [14] 黄海松, 魏建安, 任竹鹏, 等. 基于失衡样本特性过采样算法与SVM的滚动轴承故障诊断[J]. 振动与冲击, 2020, 39(10): 65-74+132 https://www.cnki.com.cn/Article/CJFDTOTAL-ZDCJ202010010.htmHUANG H S, WEI J A, REN Z P, et al. Rolling bearing fault diagnosis based on imbalanced sample characteristics oversampling algorithm and SVM[J]. Journal of Vibration and Shock, 2020, 39(10): 65-74+132 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZDCJ202010010.htm [15] YANG X S, DEB S. Engineering optimisation by cuckoo search[J]. International Journal of Mathematical Modelling and Numerical Optimisation, 2010, 1(4): 330-343 [16] LIU C F, ZHU L D, NI C B. Chatter detection in milling process based on VMD and energy entropy[J]. Mechanical Systems and Signal Processing, 2018, 105: 169-182 [17] 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 [18] YAN X A, JIA M P. Application of CSA-VMD and optimal scale morphological slice bispectrum in enhancing outer race fault detection of rolling element bearings[J]. Mechanical Systems and Signal Processing, 2019, 122: 56-86 [19] 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 https://www.cnki.com.cn/Article/CJFDTOTAL-ZGJX201804003.htmMA 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) https://www.cnki.com.cn/Article/CJFDTOTAL-ZGJX201804003.htm [20] SMITH W A, RANDALL R B. Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study[J]. Mechanical Systems and Signal Processing, 2015, 64-65: 100-131