作者：钟勇¹, 李三雁¹, 荣本阳², 张彬^2,3, 唐诗佳¹

作者单位：1. 四川大学锦城学院，四川 成都 611731;
2. 重庆邮电大学先进制造工程学院，重庆 400065;
3. 重庆大学 机械传动国家重点实验室，重庆 400044

关键词：滚动轴承;退化状态评估;排列熵;集成支持向量机;振动监测

摘要：

针对滚动轴承振动监测信号的非平稳、非线性、非高斯等复杂特点，提出一种基于排列熵和集成支持向量机的退化状态评估方法。通过自适应噪声完备集合经验模态分解算法分解得到振动信号的本征模态函数，再以重构相空间分析本征模态函数的排序模式、提取排列熵作为滚动轴承状态特征，最后利用集成支持向量机来实现不同退化状态的智能评估。滚动轴承正常、内圈和滚动体不同退化程度下的实验数据分析结果表明，与样本熵特征、支持向量机模型相比，基于排列熵的集成支持向量机获得了更高的评估准确率，该文方法可以有效用于滚动轴承的退化评估。

Degradation status assessment for rolling element bearings based on vibration signal permutation entropy and ensemble support vector machine
ZHONG Yong¹, LI Sanyan¹, RONG Benyang², ZHANG Bin^2,3, TANG Shijia¹
1. Sichuan University Jingcheng College, Chengdu 611731, China;
2. School of Advanced Manufacturing Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China;
3. State Key Laboratory of Mechanical Transmissions, Chongqing University, Chongqing 400044, China
Abstract: Aiming at the intricate non-stationary, non-linear and non-Gaussian characteristics of the vibration monitoring signal for rolling element bearings, a degradation status assessment method based on permutation entropy and ensemble support vector machine is proposed in this paper. The vibration signal was firstly decomposed by the complete ensemble empirical mode decomposition with adaptive noise to obtain intrinsic mode functions, then the order patterns of intrinsic mode functions were analyzed in the reconstructed phase space to extract permutation entropy as the condition features for rolling element bearings, and finally the ensemble support vector machine was utilized for intelligent evaluation of different degradation status. The experimental results of rolling element bearings under normal condition and different degrading severities with inner raceway and rolling element validates that, in comparison with the sample entropy feature and the support vector machine model, the proposed method achieves higher assessment accuracy. Thus the proposed method can be effectively utilized to evaluate degradation status of rolling element bearings.
Keywords: rolling element bearings;degradation status assessment;permutation entropy;ensemble support vector machine;vibration monitoring
2021, 47(7):13-18  收稿日期: 2020-10-19;收到修改稿日期: 2020-12-24
基金项目: 重庆大学机械传动国家重点实验室开放课题基金（SKLMT-KFKT-201809）
作者简介: 钟勇(1986-),男,四川成都市人,讲师,硕士,主要从事机械动态测试与信号处理研究工作
参考文献
[1] WU J, WU C, CAO S, et al. Degradation data-driven time-to-failure prognostics approach for rolling element bearings in electrical machines[J]. IEEE Transactions on Industrial Electronics, 2019, 66(1): 529-539
[2] 朱永生, 张盼, 袁倩倩, 等. 智能轴承关键技术及发展趋势[J]. 振动、测试与诊断, 2019, 39(3): 455-462+665
[3] 赵磊, 张永祥, 朱丹宸. 复杂装备滚动轴承的故障诊断与预测方法研究综述[J]. 中国测试, 2020, 46(3): 17-25
[4] 黄海凤, 高宏力, 李丹, 等. 滚动轴承早期性能退化评估技术研究[J]. 机械科学与技术, 2017, 36(11): 1771-1777
[5] 周建民, 黎慧, 张龙, 等. 基于EMD和逻辑回归的轴承性能退化评估[J]. 机械设计与研究, 2016, 32(5): 72-75+79
[6] 肖顺根, 马善红, 宋萌萌, 等. 基于EEMD和PCA滚动轴承性能退化指标的提取方法[J]. 江南大学学报(自然科学版), 2015, 14(5): 572-579
[7] LV Y, YUAN R, WANG T, et al. Health degradation monitoring and early fault diagnosis of a rolling bearing based on CEEMDAN and improved MMSE[J]. Materials, 2018, 11(6): 1009
[8] 白丽丽, 韩振南, 任家骏, 等. 基于CEEMDAN和排列熵的滚动轴承故障诊断方法[J]. 轴承, 2019(11): 54-59
[9] TORRES M E, COLOMINAS M A, SCHLOTTHAUER G, et al. A complete ensemble empirical mode decomposition with adaptive noise[C]//IEEE International Conference on Acoustics, Speech and Signal Processing, Prague, Czech Republic, 2011.
[10] BANDT C, POMPE B. Permutation entropy: A natural complexity measure for time series[J]. Physical review letters, 2002, 88(17): 174102
[11] VAPNIK V N. An overview of statistical learning theory[J]. IEEE Transactions on Neural Networks, 1999, 10(5): 988-999
[12] ZHENG J, PAN H, CHENG J. Rolling bearing fault detection and diagnosis based on composite multiscale fuzzy entropy and ensemble support vector machines[J]. Mechanical Systems and Signal Processing, 2017, 85: 746-759