Early Fault Diagnosis of Bearing Coupling Autocorrelation and Grey Relational Degree
-
摘要: 针对滚动轴承性能衰退指标敏感度低且退化起始点难以检测的问题,本文提出了自相关函数结合灰色关联度(Autocorrelation function and gray relational degree,AF-GRD)的轴承早期故障诊断方法。首先,基于希尔伯特变换和自相关函数处理轴承全寿命数据样本组获得自相关系列函数。然后,提取轴承运行初期的第一组数据作为参考样本,计算其余样本和参考样本的灰色关联度并构建轴承性能衰退指标。最后,根据该指标的变化趋势和健康阈值确定轴承早期故障发生的时间段,截取该时段的数据样本进行希尔伯特包络谱分析实现轴承早期故障诊断。利用实验室数据库完成对轴承早期故障诊断,结果表明:所提方法敏感度高而且可以完成轴承早期退化检测。Abstract: Aiming at the low sensitivity of rolling bearing performance degradation index and difficulty in determining the starting point of degradation, an early fault diagnosis method of bearing coupling autocorrelation function and gray relational degree (AF-GRD) is proposed. Firstly, the autocorrelation series function is obtained based on the Hilbert transform and the AF by processing the life data sample group of bearing. Then, the first set of data in the early stage of bearing operation was extracted as a reference sample, the GRD between the remaining samples and the reference sample was calculated and the bearing performance degradation index was constructed. Finally, the time period of the early fault of bearing is determined according to the change in index and health threshold, the data sample of this period are intercepted for Hilbert envelope spectrum analysis to realize early fault diagnosis. Using the laboratory database to complete early fault diagnosis of the bearing, the results show that AF-GRD has high sensitivity and can detect the early degradation of bearings.
-
Key words:
- bearing /
- autocorrelation function /
- grey relational degree /
- early fault diagnosis
-
表 1 7种方法的早期故障诊断结果对比
Table 1. Comparison of early fault diagnosis results of seven methods
指标方法 轴承早期故障起始点 误报警情况 AF-GRD 第533组状态样本 无 DSHDD和模糊评价 第533组状态样本 多个误报警 t-SNE和核马氏距离 第535组状态样本 无 FEEMD-EHNR 第535组状态样本 无 AVMD-EHNR 第536组状态样本 无 EHNR 第544组状态样本 无 Kurtosis 第646组状态样本 1个误报警 -
[1] DONG S Z, WEN G R, LEI Z H, et al. Transfer learning for bearing performance degradation assessment based on deep hierarchical features[J]. ISA Transactions, 2021, 108: 343-355. doi: 10.1016/j.isatra.2020.09.004 [2] LI X Q, JIANG H K, XIONG X, et al. Rolling bearing health prognosis using a modified health index based hierarchical gated recurrent unit network[J]. Mechanism and Machine Theory, 2019, 133: 229-249. doi: 10.1016/j.mechmachtheory.2018.11.005 [3] SINGH J, DARPE A K, SINGH S P. Bearing damage assessment using Jensen-Rényi divergence based on EEMD[J]. Mechanical Systems and Signal Processing, 2017, 87: 307-339. doi: 10.1016/j.ymssp.2016.10.028 [4] CHEGINI S N, MANJILI M J H, BAGHERI A. New fault diagnosis approaches for detecting the bearing slight degradation[J]. Meccanica, 2020, 55(1): 261-286. doi: 10.1007/s11012-019-01116-x [5] 吕明珠, 刘世勋, 苏晓明, 等. 基于自适应变分模态分解和包络谐噪比的滚动轴承早期退化检测[J]. 振动与冲击, 2021, 40(13): 271-280.LYU M Z, LIU S X, SU X M, et al. Early degradation detection of rolling bearing based on adaptive variational mode decomposition and envelope harmonic to noise ratio[J]. Journal of Vibration and Shock, 2021, 40(13): 271-280. (in Chinese) [6] LI Y F, LIANG X H, LIN J H, et al. Train axle bearing fault detection using a feature selection scheme based multi-scale morphological filter[J]. Mechanical Systems and Signal Processing, 2018, 101: 435-448. doi: 10.1016/j.ymssp.2017.09.007 [7] 卢绪祥, 苏一鸣, 吴家腾, 等. 基于EMD及灰色关联度的滑动轴承润滑状态故障诊断研究[J]. 动力工程学报, 2016, 36(1): 42-47. doi: 10.3969/j.issn.1674-7607.2016.01.007LU X X, SU Y M, WU J T, et al. Fault diagnosis on lubrication state of journal bearings based on EMD and grey relational degree[J]. Journal of Chinese Society of Power Engineering, 2016, 36(1): 42-47. (in Chinese) doi: 10.3969/j.issn.1674-7607.2016.01.007 [8] 杨超, 杨晓霞, 李灵飞. 基于灰色关联度和ELM的轴承性能退化趋势预测[J]. 组合机床与自动化加工技术, 2019(11): 105-108. doi: 10.13462/j.cnki.mmtamt.2019.11.026YANG C, YANG X X, LI L F. Prediction of bearing performance degradation trend based on grey relational degree and ELM[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2019(11): 105-108. (in Chinese) doi: 10.13462/j.cnki.mmtamt.2019.11.026 [9] 张俊甲, 马增强, 王梦奇, 等. 基于VMD与自相关分析的滚动轴承故障特征提取[J]. 电子测量与仪器学报, 2017, 31(9): 1372-1378.ZHANG J J, MA Z Q, WANG M Q, et al. Rolling bearing fault feature extraction based on VMD and autocorrelation analysis[J]. Journal of Electronic Measurement and Instrumentation, 2017, 31(9): 1372-1378. (in Chinese) [10] 章雅楠, 孙建平, 刘新月. 基于改进Elman神经网络的故障诊断模型研究[J]. 华北电力大学学报, 2021, 48(1): 76-84.ZHANG Y N, SUN J P, LIU X Y. Research on fault diagnosis model based on improved Elman neural network[J]. Journal of North China Electric Power University, 2021, 48(1): 76-84. (in Chinese) [11] XU X Q, ZHAO M, LIN J, et al. Envelope harmonic-to-noise ratio for periodic impulses detection and its application to bearing diagnosis[J]. Measurement, 2016, 91: 385-397. doi: 10.1016/j.measurement.2016.05.073 [12] 赵志宏, 李乐豪, 杨绍普, 等. 一种无监督的轴承健康指标及早期故障检测方法[J]. 中国机械工程, 2022, 33(10): 1234-1243. doi: 10.3969/j.issn.1004-132X.2022.10.013ZHAO Z H, LI L H, YANG S P, et al. An unsupervised bearing health indicator and early fault detection method[J]. China Mechanical Engineering, 2022, 33(10): 1234-1243. (in Chinese) doi: 10.3969/j.issn.1004-132X.2022.10.013 [13] 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(3-4): 127-140. doi: 10.1016/j.aei.2004.08.001 [14] 胡启国, 杜春超, 罗棚. 基于t-SNE和核马氏距离的滚动轴承健康状态评估[J]. 组合机床与自动化加工技术, 2021(8): 57-61.HU Q G, DU C C, LUO P. Health status evaluation of rolling bearing based on t-SNE and kernel mahalanobis distance[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2021(8): 57-61. (in Chinese) [15] 周建民, 尹文豪, 游涛, 等. 结合DSHDD和模糊评价的滚动轴承退化状态在线识别[J]. 振动工程学报, 2021, 34(3): 646-653.ZHOU J M, YIN W H, YOU T, et al. Online identification of rolling bearing degradation state based on DSHDD and fuzzy evaluation[J]. Journal of Vibration Engineering, 2021, 34(3): 646-653. (in Chinese)