基于SK等指标和SVM的滚动轴承性能退化评估研究

doi:10.16180/j.cnki.issn1007-7820.2020.01.002

摘要/Abstract

摘要：

文中提出一种基于谱峭度等指标和支持向量机的滚动轴承性能退化评估的新方法。针对滚动轴承全寿命过程中各个时期故障损伤程度的不同,将故障监测分为4个阶段:正常、初期、中期、末期。通过与传统指标,例如均方根值、峭度值、峰峰值指标等对比,验证了谱峭度作为初期故障特征指标的优势。选取谱峭度等指标作为特征输入,构建多分类支持向量机预测模型来预测轴承性能退化阶段。使用轴承全寿命试验数据对预测模型进行检验,证明了该方法的有效性和可行性。

关键词: 谱峭度, 多分类支持向量机, 故障监测, 滚动轴承, 性能退化评估, 机器学习

Abstract:

A new method for performance degradation evaluation of rolling bearings based on multiple support vector machine and indicator selection was proposed in this paper. The degree of fault at different stage in rolling bearing full life is different. In the study, fault monitoring was divided into 4 parts including normal stage, incipient stage, mid-term stage and final stage. The advantages of spectral kurtosis which was sensitive to incipient fault was demonstrated by comparing with traditional indicators such as RMS, kurtosis value and peak to peak value etc. Then, the spectral kurtosis and other indicators were selected as inputs, and the multi-class support vector machine prediction model was constructed to predict the degradation stage of rolling bearing. The prediction model was finally tested by bearing full-life test data, which verified the effectiveness and feasibility of the method and had practical engineering significance.

Key words: spectral kurtosis, multi-class support vector machine, fault monitoring, rolling bearing, performance degradation assessment, machine learning

中图分类号:

TP391

李超,郭瑜. 基于SK等指标和SVM的滚动轴承性能退化评估研究[J]. 电子科技, 2020, 33(1): 6-12.

LI Chao,GUO Yu. Research on Performance Evaluation of Rolling Bearing Performance Based on SK and Other Indicators and SVM[J]. Electronic Science and Technology, 2020, 33(1): 6-12.

图/表 15

表1

图1

图2

图3

图4

图5

图6

表2

图7

表3

图8

图9

图10

图11

表4

参考文献 17

[1]	窦东阳, 赵英凯 . 基于EMD和Lempel-Ziv指标的滚动轴承损伤程度识别研究[J]. 振动与冲击, 2010,29(3):5-8.
	Dou Dongyang, Zhao Yingkai . Fault severity assessment for rolling element bearings based on EMD and Lempel-Ziv index[J]. Journal of Vibration & Shock, 2010,29(3):5-8.
[2]	Gebraeel N, Lawley M, Liu R , et al. Residual life predictions from vibration-based degradation signals: a neural network approach[J]. IEEE Transactions on Industrial Electronics, 2004,51(3):694-700.
[3]	申中杰, 陈雪峰, 何正嘉 , 等. 基于相对特征和多变量支持向量机的滚动轴承剩余寿命预测[J]. 机械工程学报, 2013,49(2):183-9.
	Shen Zhongjie, Chen Xuefeng, He Zhenghao , et al. Remaining life prognostics of rolling bearing based on relative features and multivariable support vector machine[J]. Proceedings of Institution of Mechanical Engineers Part C Journal of Mechanical Engineering Science, 2013,227(12):2849-2860.
[4]	朱耀楚, 范玉刚 . 基于Internet的轴承运行状态远程监测系统设计[J]. 电子科技, 2018,31(5):23-26,36.
	Zhu Yaochu, Fan Yugang . The remote monitoring system for bearing running status based on Internet[J]. Electronic Science and Technology, 2018,31(5):23-26,36.
[5]	郭瑜, 郑华文, 高艳 , 等. 基于谱峭度的滚动轴承包络分析[J]. 振动、测试与诊断, 2011,31(4):517-521.
	Guo Yu, Zheng Huawen, Gao Yan , et al. Analysis of rolling bearing envelope based on spectral kurtosis[J]. Journal of Vibration, Measurement and Diagnosis, 2011,31(4):517-521.
[6]	Antoni J, Randall R B . The spectral kurtosis: application to the vibratory surveillance and diagnostics of rotating machines[J]. Mechanical Systems & Signal Processing, 2006,20(2):308-331.
[7]	Antoni J, Randall R B . The spectral kurtosis: application to the vibratory surveillance and diagnostics of rotating machines[J]. Mechanical Systems & Signal Processing, 2006,20(2):308-31.
[8]	奚立峰, 黄润青, 李兴林 , 等. 基于神经网络的球轴承剩余寿命预测[J]. 机械工程学报, 2007,43(10):137-143.
	Xi Lifeng, Huang Runqing, Li Xinglin , et al. Residual life predictions for ball bearing based on neural networks[J]. Chinese Journal of Mechanical Engineering, 2007,43(10):137-143.
[9]	Vapnik V N . An overview of statistical learning theory[J]. IEEE Transactions on Neural Networks, 1999,10(5):988-999.
[10]	Knerr S, Personnaz L, Dreyfus G . Neurocomputing[M]. Berlin:Heidelberg,Springer, 1990.
[11]	Krebel U. Advances in kernel methods[M]. Cambridge: MIT Press, 1999.
[12]	Hsu C W, Lin C J . A comparison of methods for multiclass support vector machines[J]. IEEE Transactions on Neural Networks, 2002(9):415-425.
[13]	Braun S, Greenspon J E. Mechanical signature analysis:theory and applications[M]. Salt Lake City: Academic Press, 1986.
[14]	Randall R B, Antoni J . Rolling element bearing diagnostics-A tutorial[J]. Mechanical Systems and Signal Processing, 2011,25(2):485-520.
[15]	Shao Y, Nezu K . Prognosis of remaining bearing life using neural networks[J]. Proceedings of the Institution of Mechanical Engineers-Part I, 2005,214(3):217-230.
[16]	Qiu H, Lee J, Lin J , et al. Robust performance degradation assessment methods for enhanced rolling element bearing prognostics[J]. Advanced Engineering Informatics, 2003,17(3):127-140.
[17]	Borghesani P, Antoni J . CS2 analysis in presence of non-Gaussian background noise-Effect on traditional estimators and resilience of log-envelope indicators[J]. Mechanical Systems & Signal Processing, 2017,31(9):378-398.

尺寸参数	值
型号	ZA-2115
滚柱数目/每列	16
滚柱直径/mm	8.401
节径/mm	71.447
接触角/(°)	15.17
试验转速/r·min^-1	2000
载荷/kN	26.67

编号	概率/%
编号	正常	初期	中期	后期
A_i	85	9	5	1
B_i	1	72	22	5
C_i	1	15	54	30
D_i	4	28	30	38

参数	数值
轴承外径/mm	52
轴承内直径/mm	25
接触角/(°)	0
滚动体直径/mm	7.938
滚动体数	9
内圈滚道直径/mm	30.562
外圈滚道直径/mm	46.438

编号	概率/%
编号	正常	初期	中期	后期
A_o	95	3	0	2
B_o	25	69	1	4
C_o	2	1	95	2
D_o	2	5	0	93