CEEMD-VMD与参数优化SVM结合的托辊轴承故障诊断

贺志军; 李军霞; 刘少伟; 秦志祥

doi:10.13433/j.cnki.1003-8728.20220290

CEEMD-VMD与参数优化SVM结合的托辊轴承故障诊断

doi: 10.13433/j.cnki.1003-8728.20220290

贺志军^{1, 2, 3,},
李军霞^{1, 2, 3, ,},
刘少伟^{1, 2, 3},
秦志祥^{1, 2, 3}

1.
太原理工大学机械与运载工程学院，太原　030024
2.
山西省矿山流体控制工程技术研究中心，太原　030024
3.
矿山流体控制国家地方联合工程实验室，太原　030024

基金项目: 国家自然基金面上项目（52174147）、中央引导地方科技发展资金项目（YDZJSX2021A023）及晋中市科技重点研发项目（Y211017）

详细信息

作者简介:
贺志军，硕士研究生，1446954407@qq.com

通讯作者:
李军霞，教授，博士生导师，bstljx@163.com

中图分类号: TH113.1；TH133.33
计量
- 文章访问数: 43
- HTML全文浏览量: 16
- PDF下载量: 1
- 被引次数: 0
出版历程
- 收稿日期: 2022-04-29
- 刊出日期: 2024-03-25

Roller Bearing Fault Diagnosis Combined CEEMD-VMD and Parameter Optimization SVM

HE Zhijun^{1, 2, 3
,},
LI Junxia^{1, 2, 3
, ,},
LIU Shaowei^{1, 2, 3},
QIN Zhixiang^{1, 2, 3}

1.
College of Mechanical and Vehicle Engineering, Taiyuan University of Technology, Taiyuan 030024, China
2.
Shanxi Research Center of Mining Fluid Control Engineering, Taiyuan 030024, China
3.
National-local Joint Laboratory of Mining Fluid Control Engineering, Taiyuan 030024, China

摘要

摘要: 针对托辊轴承工作环境复杂、提取故障特征困难等问题，提出一种基于互补集合经验模态分解（Complementary ensemble empirical mode decomposition, CEEMD）和变分模态分解（Variational modal decomposition, VMD）相结合的降噪方法。首先，利用CEEMD将采集到的信号进行分解，依据相关系数和峭度筛选分量并进行重构，生成新的信号；然后，利用VMD将新的信号进行再分解，并基于包络熵和包络谱峭度组合的复合指标优选本征模态分量(Intrinsic mode functions, IMF)；最后，提取相应的特征输入樽海鞘群优化支持向量机 (Salp swarm optimization support vector machine, SSO-SVM)模型完成故障诊断。实验结果表明：对于正常轴承、轴承内圈故障、轴承外圈故障三种情况，诊断准确率达97.78%。与单一降噪方法相比，该方法可以有效提高故障信号的信噪比，降噪效果明显。
- 变分模态分解 /
- 托辊轴承 /
- 樽海鞘群算法 /
- 支持向量机 /
- 故障诊断
Abstract: In order to solve the difficulty in extracting fault features of roller bearings under complex working environment, a noise reduction method was proposed based on the combination of complementary ensemble empirical mode decomposition (CEEMD) and variational modal decomposition (VMD). Firstly, the collected signals are decomposed by CEEMD, and the components are screened and reconstructed according to the correlation coefficient and kurtosis to generate new signals. Then, VMD was used to decompose the new signal, and the intrinsic mode functions (IMF) were optimized based on the composite index of the combination of envelope entropy and envelope spectrum kurtosis. Finally, the corresponding features were extracted and input into salp swarm optimized support vector machine (SSO-SVM) model to complete the fault diagnosis. The experimental results show that the diagnosis accuracy of normal bearing, bearing inner ring fault and bearing outer ring fault is up to 97.78%. Compared with the single noise reduction method, this method can effectively improve the signal noise ratio of fault signal, and the noise reduction effect is obvious.
- variational modal decomposition(VMD) /
- rolling bearing /
- salp swarm algorithm (SSO) /
- support vector machines (SVM) /
- fault diagnosis

HTML全文

图 1 SSO-SVM流程

Figure 1. SSO-SVM flow chart

下载: 全尺寸图片幻灯片

图 2 诊断模型图

Figure 2. Diagnostic model

下载: 全尺寸图片幻灯片

图 3 轴承工况图

Figure 3. Bearing working conditions

下载: 全尺寸图片幻灯片

图 4 托辊轴承实验台

Figure 4. Idler bearing test bench

下载: 全尺寸图片幻灯片

图 5 托辊轴承3种工况时域波形图

Figure 5. Time domain waveform of three working conditions of an idler bearing

下载: 全尺寸图片幻灯片

图 6 峭度值（经CEEMD分解的外圈故障信号）

Figure 6. Kurtosis values (outer ring fault signal decomposed by CEEMD)

下载: 全尺寸图片幻灯片

图 7 相关系数（经CEEMD分解的外圈故障信号）

Figure 7. Correlation coefficients (outer ring fault signal decomposed by CEEMD)

下载: 全尺寸图片幻灯片

图 8 VMD各模态分量的波形图

Figure 8. Waveform of each mode component of VMD

下载: 全尺寸图片幻灯片

图 9 IMF复合指标评价图

Figure 9. IMF composite index evaluation

下载: 全尺寸图片幻灯片

图 10 SSO-SVM分类模型图

Figure 10. SSO-SVM classification model

下载: 全尺寸图片幻灯片

图 11 CEEMD处理信号的包络谱图

Figure 11. Envelope spectrum of CEEMD processed signals

下载: 全尺寸图片幻灯片

图 12 VMD处理信号的包络谱图

Figure 12. Envelope spectrum of VMD processed signals

下载: 全尺寸图片幻灯片

图 13 本文方法处理的包络谱图

Figure 13. Envelope spectra processed by this method

下载: 全尺寸图片幻灯片

表 1 外圈故障3种降噪方法的评价指标

Table 1. Evaluation indexes of three noise reduction methods for outer ring faults

评价指标 CEEMD降噪 VMD降噪 CEEMD-VMD降噪

SNR 1.3584 2.4583 3.2439
RMSE 0.5267 0.3875 0.1254

下载: 导出CSV

表 2 不同分类器结果对比

Table 2. Comparison of results of different classifiers

识别方法平均识别率/% 测试用时/s

GA-SVM 91.11 2.38
SSA-SVM 88.89 2.20
SSO-SVM 97.78 1.46

下载: 导出CSV

参考文献(18)

[1]	LIU X W, PEI D L, LODEWIJKS G, et al. Acoustic signal based fault detection on belt conveyor idlers using machine learning[J]. Advanced Powder Technology, 2020, 31(7): 2689-2698. doi: 10.1016/j.apt.2020.04.034
[2]	苏耀瑞. 远程带式输送机托辊非接触式故障识别方法研究[D]. 银川: 宁夏大学, 2021. SU Y R. Research on non-contact fault identification method of remote belt conveyor roller[D]. Yinchuan: Ningxia University, 2021. (in Chinese)
[3]	邱明权. 矿用带式输送机托辊健康监测方法研究[D]. 徐州: 中国矿业大学, 2018. QIU M Q. Research on health monitoring method of mine belt conveyor idler[D]. Xuzhou: China University of Mining and Technology, 2018. (in Chinese)
[4]	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.
[5]	WU Z H, HUANG N E. Ensemble empirical mode decomposition: a noise-assisted data analysis method[J]. Advances in Adaptive Data Analysis, 2009, 1(1): 1-41. doi: 10.1142/S1793536909000047
[6]	YEH J R, SHIEH J S, HUANG N E. Complementary ensemble empirical mode decomposition: a novel noise enhanced data analysis method[J]. Advances in Adaptive Data Analysis, 2010, 2(2): 135-156. doi: 10.1142/S1793536910000422
[7]	曹玲玲, 李晶, 彭镇, 等. 基于改进小波阈值降噪的滚动轴承故障诊断方法[J]. 振动工程学报, 2022, 35(2): 454-463. CAO L L, LI J, PENG Z, et al. Rolling bearing fault diagnosis method based on improved wavelet threshold denoising[J]. Journal of Vibration Engineering, 2022, 35(2): 454-463. (in Chinese)
[8]	DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544. doi: 10.1109/TSP.2013.2288675
[9]	任朝晖, 于天壮, 丁东, 等. 基于VMD-DBN的滚动轴承故障诊断方法[J]. 东北大学学报(自然科学版), 2021, 42(8): 1105-1110. REN Z H, YU T Z, DING D, et al. Fault diagnosis method of rolling bearing based on VMD-DBN[J]. Journal of Northeastern University (Natural Science), 2021, 42(8): 1105-1110. (in Chinese)
[10]	郝家琦, 徐金海, 鲍超超, 等. 基于VMD与SVM的电梯鼓式制动器故障诊断研究[J]. 机电工程, 2022, 39(1): 112-119. HAO J Q, XU J H, BAO C C, et al. Fault diagnosis of elevator drum brake based on VMD and SVM[J]. Journal of Mechanical & Electrical Engineering, 2022, 39(1): 112-119. (in Chinese)
[11]	杜占涛, 纪爱敏, 陈曦晖, 等. 基于ISVD多级降噪和SVM的轴承故障诊断研究[J]. 机电工程, 2022, 39(5): 567-577. DU Z T, JI A M, CHEN X H, et al. Bearing fault diagnosis based on ISVD multi-stage noise reduction and SVM[J]. Journal of Mechanical and Electrical Engineering, 2022, 39(5): 567-577. (in Chinese)
[12]	周建民, 王发令, 张臣臣, 等. 基于特征优选和GA-SVM的滚动轴承智能评估方法[J]. 振动与冲击, 2021, 40(4): 227-234. ZHOU J M, WANG F L, ZHANG C C, et al. An intelligent method for rolling bearing evaluation using feature optimization and GA-SVM[J]. Journal of Vibration and Shock, 2021, 40(4): 227-234. (in Chinese)
[13]	李怡, 李焕锋, 刘自然. 基于CEEMDAN多尺度熵和SSA-SVM的滚动轴承故障诊断研究[J]. 机电工程, 2021, 38(5): 599-604. LI Y, LI H F, LIU Z R. Fault diagnosis of rolling bearing based on CEEMDAN multi-scale entropy and SSA-SVM[J]. Journal of Mechanical and Electrical Engineering, 2021, 38(5): 599-604. (in Chinese)
[14]	王振亚, 姚立纲, 戚晓利, 等. 参数优化变分模态分解与多域流形学习的行星齿轮箱故障诊断[J]. 振动与冲击, 2021, 40(1): 110-118. WANG Z Y, YAO L G, QI X L, et al. Fault diagnosis of planetary gearbox based on parameter optimized VMD and multi-domain manifold learning[J]. Journal of Vibration and Shock, 2021, 40(1): 110-118. (in Chinese)
[15]	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. doi: 10.7652/xjtuxb201505012 TANG 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) doi: 10.7652/xjtuxb201505012
[16]	MIRJALILI S, GANDOMI A H, MIRJALILI S Z, et al. Salp swarm algorithm: a bio-inspired optimizer for engineering design problems[J]. Advances in Engineering Software, 2017, 114: 163-191. doi: 10.1016/j.advengsoft.2017.07.002
[17]	王振亚, 姚立纲, 蔡永武, 等. 基于熵-流特征和樽海鞘群优化支持向量机的故障诊断方法[J]. 振动与冲击, 2021, 40(6): 107-114. WANG Z Y, YAO L G, CAI Y W, et al. Fault diagnosis method based on the entropy-manifold feature and SSO-SVM[J]. Journal of Vibration and Shock, 2021, 40(6): 107-114. (in Chinese)
[18]	乔美英, 刘宇翔, 兰建义. 基于VMD和马氏距离SVM的滚动轴承故障诊断[J]. 中山大学学报(自然科学版), 2019, 58(5): 8-16. QIAO M Y, LIU Y X, LAN J Y. Fault diagnosis method of rolling bearings based on VMD and mahalanobis distance SVM[J]. Acta Scientiarum Naturalium Universitatis Sunyatseni, 2019, 58(5): 8-16. (in Chinese)