基于特征优选和GA-SVM的滚动轴承智能评估方法

摘要
图/表
参考文献(22)
相关文章 (15)

全文: PDF (1612 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要

针对滚动轴承等旋转机械设备零部件的退化状态识别问题，研究并提出一种基于支持向量机（Support vector machine，SVM）的智能评估方法。对于在线持续输出的轴承振动信号，采用时域方法和集成经验模态分解（Ensemble empirical mode decomposition，EEMD）能量熵提取轴承特征，并基于相关性、单调性和鲁棒性进行特征选择。综合考虑三个指标，计算选择准则，得到最终的退化特征。针对SVM参数选择困难问题，使用遗传算法（Genetic algorithm，GA）优化SVM参数，确定参数最优值。定义轴承性能退化指标，用三种不同故障类型的轴承数据训练模型。分别输入不同故障的轴承全寿命周期数据，得到轴承故障的类型和性能退化曲线，确定早期故障点。最后对方法进行对比和验证。实验表明，模型故障诊断平均准确率为97.69%，性能退化评估曲线结果准确，早期故障检测能力强。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	周建民
	王发令
	张臣臣
	张龙
	尹文豪
	李鹏

关键词 ：滚动轴承, 性能退化评估, 集成经验模态分解, 特征选择, 遗传算法, 支持向量机

Abstract：Condition monitoring and fault diagnosis of rolling bearings is one of the hotspots in the research of rotating machinery fault diagnosis.For the problem of degenerative state identification of rotating machinery such as rolling bearings, an intelligent diagnosis method based onsupport vector machine was proposed.For the bearing vibration signal of continuous output on the line, a time domain method and the ensemble empirical mode decomposition (EEMD) energy entropy were used to extract the bearing characteristics, and the feature selection was based on correlation, monotonicity, and robustness.Considering three indicators comprehensively, the selection criteria were calculated to obtain the final degradation characteristics.For the problem of parameter selection of support vector machine, the genetic algorithm (GA) was used to optimize the SVM parameters and determine the optimal values of the parameters.The bearing performance degradation state health indicators were defined, and the model was trained with bearing data from three different fault types.The bearing life cycle data of different faults were input separately, and the type of bearing fault and the performance degradation curve were obtained to determine the early fault point.Finally, the method was compared and verified.Experiments show that the average accuracy of model fault diagnosis is 97.69%, the performance degradation assessment curve is accurate, and the early fault detection capability is strong.

Key words： rolling bearing performance degradation assessment ensemble empirical mode decomposition(EEMD) feature selection genetic algorithm(GA) support vector machine(SVM)

收稿日期: 2019-11-20 出版日期: 2021-02-28

引用本文:

周建民，王发令，张臣臣，张龙，尹文豪，李鹏. 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 Jianmin, WANG Faling, ZHANG Chenchen, ZHANG Long, YIN Wenhao, LI Peng. An intelligent method for rolling bearing evaluation using feature optimization and GA-SVM. JOURNAL OF VIBRATION AND SHOCK, 2021, 40(4): 227-234.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2021/V40/I4/227

[1] WangY, XuGH, ZhangQ, et al.Rotating speed isolation and its application to rolling element bearing fault diagnosis under large speed variation conditions[J]. Journal of Sound and Vibration, 2015, 348:381-396.
[2] 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):227-233.
Li 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):227-233.
[3] 夏均忠, 吕麒鹏, 陈成法, 等. 基于JRD和CUSUM的滚动轴承性能退化状态识别和评估[J]. 振动与冲击, 2019, 38(2):1-5.
Xia JZ, Lv QP, Chen CF, et al. Performance degradation status identification and assessment of rolling element bearing [J]. Journal of Vibration and Shock, 2019, 38(2):1-5.
[4] Gai JB, Hu YF and Shen JX. A bearing performance degradation modeling method based on EMD-SVD and fuzzy neural network [J]. Shock and Vibration. 2019:1-10.
[5] Malik H, Ashish Y and Kumar SA. EMD and ANN based intelligent model for bearing fault diagnosis[J]. Journal of Intelligent & Fuzzy Systems, 2018,35(5):5391-5402.
[6] 蔡艳平, 李艾华, 石林锁,等. EMD端点效应的改进型混沌延拓方法及其在机械故障诊断中的应用[J]. 振动与冲击, 2011, 30(11):46-52.
Cai YP, Li AH, Shi LS, et al. Processing method for end effects of EMD based on improvedchaos forecasting model and its application in machinery fault diagnosis[J]. Journal of Vibration and Shock, 2011, 30(11):46-52.
[7] Wu ZH and Huang NE. Ensemble empirical mode decomposition: A nosie-assisted data analysis method[J]. Advances in Adaptive Data Analysis, 2009,1(1):1-41.
[8] Chen HG, ChenP, ChenWH, et al. Wind turbine gearbox fault diagnosis based on improved EEMD andHilbert square demodulation[J]. Applied Sciences-Basel. 2017, 7(2), 128.
[9] 陈法法, 李冕, 陈保家, 等. EEMD能量熵与优化LS-SVM的滚动轴承故障诊断[J]. 组合机床与自动化加工技术, 2016(12):71-75.
Chen FF, Li M, Chen JB, et al. The roller bearing fault diagnosis based on EEMD energy entropy and LS-SVM[J]. Modular Machine Tool&Automatic Manufacturing Technique, 2016(12):71-75.
[10] Wang Y, Kang S, Jiang Y, et al. Classification of fault location and the degree of performance degradation of a rollingbearing based on an improved hyper-sphere-structured multi-class support vector machine[J].Mechanical Systems and Signal Processing. 2012,29: 404-414.
[11] ZhangXY, LiangYT., ZhouJZ, et al. A novel bearing fault diagnosis model integrated permutation entropy, ensemble empirical mode decomposition and optimized SVM[J].Measurement, 2015,69:164–179.
[12] 陈龙, 谭继文, 管皓. 基于单层SAE与SVM的滚动轴承性能退化评估[J]. 机床与液压, 2018(1):164-168.
Chen L, Tan JW and Guan H. Performance degradation assessment for rolling bearing basedon single layer SAE and SVM[J]. Machine Tool & Hydraulics, 2018(1):164-168.
[13] Huang NE, Shen Z, Long SR, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear non-stationary time series analysis [J]. Proceedings of the Royal Society, 1998(454); 903-905.
[14] 侯高雁, 吕勇, 肖涵,等. 基于EEMD自适应形态学在齿轮故障诊断中的应用[J]. 振动与冲击, 2014, 33(18):145-148.
Hou GY, Lu Y, Xiao H, et al. Application of adaptive morphology in gear fault diagnosis based on EEMD [J]. Journal of Vibration and Shock, 2014, 33(18):145-148.
[15] Ben AliJ, Fnaiech N, Saidi L, et al. Application of empirical mode decomposition and artificial neural network for automatic bearing fault diagnosis based on vibration signals [J]. Applied Acoustics, 2015,89:16-27.
[16] Wu B, Li W and Qiu MQ. Remaining useful life prediction ofbearing with vibration signals based on a novel indicator [J].Shock and Vibration, 2017.
[17] Zhang B, Zhang LJ and Xu JW, Degradation feature selectionfor remaining useful life prediction of rolling element bearings[J]. Quality and Reliability Engineering International, 2016,32(2): 547-554.
[18] 皮骏, 马圣, 贺嘉城, 等. 基于IGA-ELM网络的滚动轴承故障诊断[J], 航空学报, 2018,39(9):233-244.
Pi J, Ma S, He JC, et al. Rolling bearing fault diagnosis based on IGA-ELM network [J]. ActaAeronauticaetAstronauticaSinica, 2018, 39(9):233-244.
[19] Li SL, Liu ZL.Application of improved wavelet packet energy entropy and GA-SVM in rolling bearing fault diagnosis [C]. 2018 IEEE International Conference on Signal Processing,Communications and Computing, 2018.
[20] Zhou JM, Wang FL, Zhang CC, et al. Evaluation of rolling bearing performancedegradation using wavelet packet energy entropyand RBF neural network [J]. Symmetry, 2019:1-14.
[21] Zhu KH, Chen L and Hu X. Rolling element bearing fault diagnosis bycombining adaptive local iterative filtering,modified fuzzy entropy and support vector machine [J]. Entropy, 2018,20(12):926.
[22] NiuLK, Cao HR, He ZJ, et al. A systematic study of ball passing frequencies based on dynamic modeling ofrolling ball bearings with localized surface defects[J].Journal of Sound and Vibration,2015, 357, 207–232.