作者：但长林1, 李三雁1, 张彬2
作者单位：1. 四川大学锦城学院智能制造学院，四川 成都 611731;
2. 重庆邮电大学先进制造工程学院，重庆 400065
关键词：滚动轴承;故障诊断;样本熵;SVM;状态监测
摘要：
滚动轴承状态监测信号一般表现出复杂的非平稳、非线性，从而需要研究非平稳信号分析与非线性特征提取的故障诊断方法。为此，该文研究一种基于振动信号分解样本熵特征和SVM分类器的滚动轴承故障诊断方法。首先，通过改进的自适应白噪声完备集合经验模态分解(ICEEMDAN)算法将原始振动信号分解成一系列的本征模态函数；然后，将本征模态函数重构到相空间，分析提取样本熵特征以描述滚动轴承的运行状态；最后，构建和训练SVM多分类器以实现滚动轴承正常、故障状态的智能诊断。滚动轴承故障模拟实验台的案例研究结果表明，基于样本熵和SVM可以较准确地进行滚动轴承不同故障模式、不同故障尺寸的诊断。
Research on fault diagnosis method for rolling element bearings based on sample entropy and SVM
DAN Changlin1, LI Sanyan1, ZHANG Bin2
1. School of Intelligent Manufacturing, Jincheng College of Sichuan University, Chengdu 611731, China;
2. School of Advanced Manufacturing Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
Abstract: The condition monitoring signals of rolling bearings are usually non-stationary and non-linear, so it is necessary to study the fault diagnosis methods based on nonstationary signal analysis and nonlinear feature extraction. Therefore, a fault diagnosis method for rolling element bearings based on sample entropy features of vibration signal components and SVM classifier was studied in this work. Firstly, the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) algorithm was used to decompose the original vibration signal into a series of intrinsic mode functions. Then these functions were reconstructed into phase space and sample entropy features were extracted to describe the bearing operational status. Finally, a multi-classifier SVM was constructed and trained to intelligently diagnosis the normal and fault states of rolling bearings. The case study results of the bearing fault simulation test-bed demonstrated that different fault modes as well as distinct fault sevrities can be accurately diagnosed by the sample entropy and SVM.
Keywords: rolling element bearings;fault diagnosis;sample entropy;SVM;condition monitoring
2020, 46(11):37-42 收稿日期: 2020-08-21;收到修改稿日期: 2020-09-29
基金项目: 重庆市教育委员会科学技术研究项目(KJ1704109)
作者简介: 但长林(1986-),男,四川仁寿县人,助理研究员,主要从事机械故障测试与诊断研究工作
参考文献
[1] RAI A, UPADHYAY S H. A review on signal processing techniques utilized in the fault diagnosis of rolling element bearings[J]. Tribology International, 2016, 96: 289-306
[2] 沙美妤, 刘利国. 基于振动信号的轴承故障诊断技术综述[J]. 轴承, 2015(9): 59-63
[3] LEI Y G, LIN J, HE Z J, et al. A review on empirical mode decomposition in fault diagnosis of rotating machinery[J]. Mechanical Systems and Signal Processing, 2013, 35: 108-126
[4] 施莹, 庄哲, 林建辉. 基于EEMD排列熵的高速列车轮对轴承故障诊断方法[J]. 中国测试, 2017, 43(11): 89-95
[5] 张洪梅, 邹金慧. 自适应MCKD和CEEMDAN的滚动轴承微弱故障特征提取[J]. 电子测量与仪器学报, 2019, 33(4): 79-86
[6] 阮荣刚, 李友荣, 易灿灿, 等. 改进的噪声总体集合经验模式分解方法在轴承故障诊断中的应用[J]. 机械设计与制造, 2019(1): 153-157
[7] 张淑清, 黄文静, 胡永涛, 等. 基于总体平均经验模式分解近似熵和混合PSO-BP算法的轴承故障诊断方法[J]. 中国机械工程, 2016, 27(22): 3048-3054
[8] 谢志谦, 孙虎儿, 刘乐, 等. 基于CEEMDAN样本熵与SVM的滚动轴承故障诊断[J]. 组合机床与自动化加工技术, 2017(3): 96-100
[9] COLOMINAS M A, SCHLOTTHAUER G, TORRES M E. Improved complete ensemble EMD: A suitable tool for biomedical signal processing[J]. Biomedical Signal Processing and Control, 2014, 14: 19-29
[10] RICHMAN J S, MOORMAN J R. Physiological time-series analysis using approximate entropy and sample entropy[J]. American Journal of Physiology-Heart and Circulatory Physiology, 2000, 278(6): 2039-2049
[11] CRISTIANINI N, SHAWE-TAYLOR J. An introduction to support vector machines and other kernel-based learning methods[M]. Cambridge : Cambridge University Press, 2000.
[12] LI Y, WANG X, SI S, et al. Entropy based fault classification using the Case Western Reserve University data: A benchmark study[J]. IEEE Transactions on Reliability, 2020, 69(2): 754-767
