基于EWM和SVR的滚动轴承剩余使用寿命预测方法

doi:10.16265/j.cnki.issn1003-3033.2023.09.2009

摘要/Abstract

摘要：

为解决滚动轴承有限全寿命监测数据情况下退化特征分布失真导致轴承剩余使用寿命(RUL)预测精度不高的问题,提出一种基于熵权法(EWM)和支持向量回归(SVR)的轴承RUL预测方法。首先,提取振动信号的时域和频域特征,并对特征进行对数变换;然后,通过EWM确定指标权重实现特征选择;最后,采用麻雀搜索算法(SSA)优化SVR模型,以主成分分析(PCA)降维后的低维特征作为优化后的SVR模型的输入,RUL占比作为输出,从而实现轴承剩余寿命的预测。结果表明:在有限监测数据情况下,与其他方法相比,所提方法不但预测性能更加稳定,而且预测的绝对误差平均降低19.51%,均方误差(MSE)平均降低17.73%。

关键词: 熵权法(EWM), 支持向量回归(SVR), 滚动轴承, 剩余使用寿命(RUL)预测, 麻雀搜索算法(SSA)

Abstract:

In order to solve the problem that the RUL prediction accuracy of rolling bearings was not high due to the distortion of degradation feature distribution under the condition of limited full-life monitoring data of rolling bearings, a prediction method of the RUL of rolling bearings based on EWM and SVR was proposed. Firstly, the time-domain and frequency-domain features of the vibration signal were extracted, and the logarithmic transformation was performed on the features. Then, the index weights were determined by EWM to realize the feature selection. Finally, SSA was used to optimize the SVR model, and the low-dimensional features after dimensionality reduction by principal component analysis(PCA) were used as the input of the optimized SVR model, and the RUL percentage was used as the output, so as to realize the prediction of the RUL of the bearing. The results show that under the condition of limited monitoring data, compared with other methods, the proposed method not only has a more stable prediction performance, but also has an average reduction of 19.51% in absolute error and 17.73% in mean square error(MSE).

Key words: entropy weight method(EWM), support vector regression(SVR), rolling bearing, remaining useful life(RUL)prediction, sparrow search algorithm(SSA)

古莹奎, 汪源金, 石昌武. 基于EWM和SVR的滚动轴承剩余使用寿命预测方法[J]. 中国安全科学学报, 2023, 33(9): 49-55.

GU Yingkui, WANG Yuanjin, SHI Changwu. Remaining useful life prediction method of rolling bearing based on EWM and SVR[J]. China Safety Science Journal, 2023, 33(9): 49-55.

图/表 13

图1

图2

表1

表2

图3

图4

图5

图6

图7

图8

图9

表3

图10

参考文献 21

[1]	LEI Yaguo, LI Naipeng, GUO Liang, et al. Machinery health prognostics: a systematic review from data acquisition to RUL prediction[J]. Mechanical Systems and Signal Processing, 2018, 104:799-834. doi: 10.1016/j.ymssp.2017.11.016
[2]	LI Feng, CHENG Yangyang, TANG Baoping, et al. Multi-layer gated temporal convolution network for residual useful life prediction of rotating machinery[J]. Mechanical Systems and Signal Processing, 2021, 155:DOI: 10.1016/j.ymssp.2020.107600.
[3]	DUAN Zhihe, WU Tonghai, GUO Shuaiwei, et al. Development and trend of condition monitoring and fault diagnosis of multi-sensors information fusion for rolling bearings: a review[J]. The International Journal of Advanced Manufacturing Technology, 2018, 96(1/2/3/4):803-819. doi: 10.1007/s00170-017-1474-8
[4]	QIU Guangqi, GU Yingkui, Chen Junjie. Selective health indicator for bearings ensemble remaining useful life prediction with genetic algorithm and Weibull proportional hazards model[J]. Measurement, 2020, 150: DOI: 10.1016/j.measurement.2019.107097.
[5]	裴洪, 胡昌华, 司小胜, 等. 基于机器学习的设备剩余寿命预测方法综述[J]. 机械工程学报, 2019, 55(8):1-13. doi: 10.3901/JME.2019.08.001
	PEI Hong, HU Changhua, SI Xiaosheng, et al. Review of machine learning based remaining useful life prediction methods for equipment[J]. Journal of Mechanical Engineering, 2019, 55(8):1-13. doi: 10.3901/JME.2019.08.001
[6]	梁伟阁, 张钢, 王健, 等. 复杂机械设备健康状态预测方法研究综述[J]. 兵器装备工程学报, 2022, 43(7):67-77.
	LIANG Weige, ZHANG Gang, WANG Jian, et al. A review on health sate assessment and remaining useful life prediction of mechanical equipment under intelligent manufacturing[J]. Journal of Ordnance Equipment Engineering, 2022, 43(7):67-77.
[7]	李海浪, 刘永志, 邹益胜, 等. 一种基于TC-CAE的轴承寿命预测方法[J]. 振动与冲击, 2022, 41(14):105-113,189.
	LI Hailang, LIU Yongzhi, ZOU Yisheng, et al. Bearing life prediction based on the method of TC-CAE[J]. Journal of Vibration and Shock, 2022, 41(14):105-113,189.
[8]	欧白羽, 杨勐, 韩旭. 基于互信息的主成分分析结合支持向量回归的滚动轴承剩余寿命预测研究[J]. 北京化工大学学报 :自然科学版, 2021, 48(6):108-117.
	OU Baiyu, YANG Meng, HAN Xu. Remaining useful life prediction of rolling bearings based on mutual information based principal component analysis combined with support vector regression[J]. Journal of Beijing University of Chemical Technology:Natural Science Edition, 2021, 48(6):108-117.
[9]	ZHANG Nannan, WU Lifeng, WANG Zhonghua, et al. Bearing remaining useful life prediction based on Naive Bayes and Weibull distributions[J]. Entropy, 2018, 20(12):944-962. doi: 10.3390/e20120944
[10]	GU Yingkui, BI Qingpeng, QIU Guangqi. Practical health indicator construction methodology for bearing ensemble remaining useful life prediction with ISOMAP-DE and ELM-WPHM[J]. Measurement Science and Technology, 2021, 33(2): DOI: 10.1088/1361-6501/ac3855.
[11]	WANG Biao, LEI Yaguo, LI Naipeng, et al. Deep separable convolutional network for remaining useful life prediction of machinery[J]. Mechanical Systems and Signal Processing, 2019, 134: DOI: 10.1016/j.ymssp.2019.106330.
[12]	杨宇, 张娜, 程军圣. 全参数动态学习深度信念网络在滚动轴承寿命预测中的应用[J]. 振动与冲击, 2019, 38(10):199-205,249.
	YANG Yu, ZHANG Na, CHENG Junsheng.. Global parameters dynamic learning deep belief networks and its application in rolling bearing life prediction[J]. Journal of Vibration and Shock, 2019, 38(10):199-205,249.
[13]	HAN Tian, PANG Jiachen, TAN Andy. Remaining useful life prediction of bearing based on stacked autoencoder and recurrent neural network[J]. Journal of Manufacturing Systems, 2021, 61:576-591. doi: 10.1016/j.jmsy.2021.10.011
[14]	YANG Xiaoyu, ZHENG Ying, ZHANG Yong, et al. Bearing Remaining useful life prediction based on regression shapalet and graph neural network[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71:1-12.
[15]	LI Yuxiong, HUANG Xianzhen, ZHAO Chengying, et al. Stochastic fractal search-optimized multi-support vector regression for remaining useful life prediction of bearings[J]. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 2021, 43(9):1-18. doi: 10.1007/s40430-020-02713-8
[16]	ZAN Tao, LIU Zhihao, WANG Hui, et al. Prediction of performance deterioration of rolling bearing based on JADE and PSO-SVM[J]. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 2021, 235(9):1684-1697. doi: 10.1177/0954406220951209
[17]	古莹奎, 孔军廷, 朱繁泷. 基于邻域属性重要度的齿轮箱故障特征优选方法[J]. 煤炭学报, 2015, 40(增2):560-567.
	GU Yingkui, KONG Junting, ZHU Fanlong. Optimal selection method of gearbox fault feature based on neighborhood attribute importance[J]. Journal of China Coal Society, 2015, 40(S2):560-567.
[18]	杨艳芳, 邢亚辉, 舒亮, 等. 基于孪生数据的设备健康度评估方法研究[J]. 华中科技大学学报:自然科学版, 2022, 50(6):97-106.
	YANG Yanfang, XING Yahui, SHU Liang, et al. Research on equipment health assessment method based on twin data[J]. Journal of Huazhong University of Science and Technology:Natural Science Edition, 2022, 50(6):97-106.
[19]	朱峰, 张宏伟. 基于“AHP+熵权法”的CW-TOPSIS冲击地压评判模型[J]. 中国安全科学学报, 2017, 27(1):128-133. doi: 10.16265/j.cnki.issn1003-3033.2017.01.023
	ZHU Feng, ZHANG Hongwei. "AHP+entropy weight method" based CW-TOPSIS model for predicting rockburst[J]. China Safety Science Journal, 2017, 27(1):128-133. doi: 10.16265/j.cnki.issn1003-3033.2017.01.023
[20]	XUE Jiankai, SHEN Bo. A novel swarm intelligence optimization approach: sparrow search algorithm[J]. Systems Science & Control Engineering, 2020, 8(1):22-34.
[21]	PATRICK N, RAFAEL G, KAMAL M, et al. PRONOSTIA: an experimental platform for bearings accelerated degradation tests[C]. Proceedings of IEEE International Conference on Prognostics and Health Management, 2012:1-8.

工况	载荷/N	转速/(r·min^-1)
1	4 000	1 800
2	4 200	1 650
3	5 000	1 500

预测方法	特征选择	预测模型
方案1	EWM	SSA-SVR
方案2	MI	SSA-SVR
方案3	EWM	PSO-SVR
方案4	EWM	LSTM

预测方法	MAE/%	MSE/%	RMSE/%
方案1	0.053 19	0.004 53	0.067 31
方案2	0.069 13	0.007 24	0.085 11
方案3	0.055 93	0.005 07	0.071 17
方案4	0.076 63	0.008 46	0.092 03