基于频域TCAE-Informer的滚动轴承剩余使用寿命预测方法

doi:10.12382/bgxb.2024.0619

摘要/Abstract

摘要：

滚动轴承是大量旋转机械中的关键部件，其剩余使用寿命(Remaining Useful Life，RUL)预测问题关系到设备能否安全稳定运行。为解决目前RUL预测精度低的问题，提出一种在频域上结合时间卷积自编码器(Temporal Convolutional Autoencoder，TCAE)和Informer网络的滚动轴承RUL预测方法(TCAE-Informer)。所提方法设计了一种TCAE，面向滚动轴承不同时间样本的频域信号，自适应地挖掘更能反映滚动轴承全寿命退化周期的深度特征；搭建起一个Informer网络模型，借助其在长序列信息上的学习优势，有效拟合出深度特征与滚动轴承RUL的映射关系，进而实现滚动轴承RUL预测功能。使用XJTU-SY轴承数据集的对比验证，对照3种RUL预测结果评价指标，所提方法在不同的工况条件下，相比现有的多种方法均能够实现较为准确的RUL预测效果，证明了所提方法具有优越的RUL预测能力和泛化能力。针对不同方法进行了抗干扰测试，所提方法在不同噪声条件下均展现出了更优的RUL预测效果，证明了所提方法具有良好的RUL预测抗干扰能力。

关键词: 滚动轴承, 剩余使用寿命预测, 时间卷积自编码器, Informer网络, 深度特征提取

Abstract:

Rolling bearing is a key component in a large number of rotating machines，and its remaining useful life (RUL) prediction is related to whether an equipment can operate safely and stably.In order to solve the current problem of low accuracy of RUL prediction，a prediction method combining temporal convolutional autoencoder (TCAE) and Informer (TCAE-Informer) network in frequency domain is proposed for RUL of rolling bearings.The method designs a TCAE for the frequency-domain signals of different time samples of rolling bearings，and adaptively extracts the depth features that better reflect the full-life degradation law of rolling bearings.An Informer network model is built，and with the help of its learning advantage in long sequence information，the mapping relationship between the depth features and the RUL of rolling bearings is effectively fitted to realize the RUL prediction function of rolling bearings.XJTU-SY bearing dataset is used to compare and validate the evaluation indexes of three RUL prediction results.The results show that the proposed method is able to achieve more accurate RUL prediction effect under different working conditions compared with many existing methods，which proves that it has superior RUL prediction ability and generalization ability.The anti-interference test is carried out for different methods.In the test，the proposed method shows better RUL prediction effect under different noise conditions，which proves that it has superior anti-interference ability of RUL prediction.

Key words: rolling bearing, remaining useful life prediction, temporal convolutional autoencoder, informer network, deep feature extraction

中图分类号:

TH17

闫昊, 李思雨, 展先彪, 董恩志, 温亮, 贾希胜. 基于频域TCAE-Informer的滚动轴承剩余使用寿命预测方法[J]. 兵工学报, 2025, 46(S1): 240619-.

YAN Hao, LI Siyu, ZHAN Xianbiao, DONG Enzhi, WEN Liang, JIA Xisheng. Remaining Useful Life Prediction Method of Rolling Bearing Based on Frequency-domain TCAE-Informer[J]. Acta Armamentarii, 2025, 46(S1): 240619-.

图/表 20

参考文献 21

[1]	许晓东, 唐圣金, 谢建, 等. 随机退化应力作用下设备剩余寿命预测方法[J]. 兵工学报, 2022, 43(3):712-719. doi: 10.12382/bgxb.2021.0018
	XU X D, TANG S J, XIE J, et al. Remaining useful life prediction of equipment under random degradation stress[J]. Acta Armamentarii, 2022, 43(3):712-719. (in Chinese) doi: 10.12382/bgxb.2021.0018
[2]	李泽东, 李志农, 陶俊勇, 等. 基于特征融合的注意力增强卷积神经网络的航空发动机滚动轴承故障诊断方法[J]. 兵工学报, 2022, 43(12):3228-3239.
	LI Z D, LI Z N, TAO J Y, et al. Fault diagnosis for aero-engine rolling bearings based on an attention augmented convolutional neural network with feature fusion[J]. Acta Armamentarii, 2022, 43(12):3228-3239. (in Chinese)
[3]	郭玉荣, 茅健, 赵嫚. 基于CNN与注意力BiLSTM的轴承剩余使用寿命预测方法[J]. 上海工程技术大学学报, 2023, 37(1):96-104.
	GUO Y R, MAO J, ZHAO M. Prediction method of bearing remaining useful life based on CNN and attention BiLSTM[J]. Journal of Shanghai University of Engineering Science, 2023, 37(1):96-104. (in Chinese)
[4]	AZYUS A F, WIJAYA S K, NAVED M. Prediction of remaining useful life using the CNN-GRU network:a study on maintenance management[J]. Software Impacts, 2023, 17:100535.
[5]	邱佩臻, 吴东燃, 夏艺, 等. 循环神经网络在剩余使用寿命预测中的应用综述[J]. 现代信息科技, 2023, 7(24):61-66.
	QIU P Z, WU D R, XIA Y. Review on the application of recurrent neural networks in the prediction of remaining service life[J]. Modern Information Technology, 2023, 7(24):61-66. (in Chinese)
[6]	DU X J, JIA W C, YU P, et al. RUL prediction based on GAM-CNN for rotating machinery[J]. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 2023, 45(3):142.
[7]	WANG F T, LIU X F, DENG G, et al. Remaining life prediction method for rolling bearing based on the long short-term memory network[J]. Neural Processing Letters, 2019, 50:2437-2454.
[8]	ZHOU J H, QIN Y, CHEN D L, et al. Remaining useful life prediction of bearings by a new reinforced memory GRU network[J]. Advanced Engineering Informatics, 2022, 53:101682.
[9]	ZHAO C Y, HUANG X Z, LI Y X, et al. A double-channel hybrid deep neural network based on CNN and BiLSTM for remaining useful life prediction[J]. Sensors, 2020, 20(24):7109.
[10]	周哲韬, 刘路, 宋晓, 等. 基于Transformer模型的滚动轴承剩余使用寿命预测方法[J]. 北京航空航天大学学报, 2023, 49(2):430-443.
	ZHOU Z T, LIU L, SONG X, et al. Remaining useful life prediction method of rolling bearing based on Transformer model[J]. Journal of Beijing University of Aeronautics and Astronautics, 2023, 49(2):430-443. (in Chinese)
[11]	马依琳, 陶慧玲, 董启文, 等. 基于Transformer的多特征融合的航空发动机剩余使用寿命预测[J]. 华东师范大学学报(自然科学版), 2022(5):219-232.
	MA Y L, TAO H L, DONG Q W, et al. Prediction of remaining useful life of aeroengines based on the Transformer with multi-feature fusion[J]. Journal of East China Normal University (Natural Science), 2022(5):219-232. (in Chinese)
[12]	SU X Y, LIU H M, TAO L F, et al. An end-to-end framework for remaining useful life prediction of rolling bearing based on feature pre-extraction mechanism and deep adaptive transformer model[J]. Computers & Industrial Engineering, 2021, 161:107531.
[13]	邓飞跃, 陈哲, 郝如江. 基于MsTCN-Transformer模型的轴承剩余使用寿命预测研究[J]. 振动与冲击, 2024, 43(4):279-287.
	DENG F Y, CHEN Z, HAO R J, et al. Research on bearing remaining useful life prediction based on an MsTCN-Transformer model[J]. Journal of Vibration and Shock, 2024, 43(4):279-287. (in Chinese)
[14]	LIU Y L, CHEN J L, CHANG Y H, et al. A novel integration framework for degradation-state prediction via transformer model with autonomous optimizing mechanism[J]. Journal of Manufacturing Systems, 2022, 64:288-302.
[15]	陈哲. 基于长时间序列分析的滚动轴承剩余使用寿命预测方法研究[D]. 石家庄: 石家庄铁道大学, 2023.
	CHEN Z. Research on prediction method of remaining useful life of rolling bearing based on long-time sequential analysis[D]. Shijiazhuang: Shijiazhuang Tiedao University, 2023. (in Chinese)
[16]	LEA C, VIDAL R, REITER A, et al. Temporal convolutional networks:a unified approach to action segmentation[C]// Proceedings of the Computer Vision-ECCV 2016 Workshops. Amsterdam, Netherlands: Springer International Publishing,2016:47-54.
[17]	ZHOU H Y, ZHANG S H, PENG J Q, et al. Informer:beyond efficient transformer for long sequence time-series forecasting[C]// Proceedings of the AAAI Conference on Artificial Intelligence.[S. l.]: 2021, 35(12):11106-11115.
[18]	ZHAN X B, LIU Z X, YAN H, et al. A two-stage framework for predicting the remaining useful life of bearings[J]. Open Physics, 2024, 22(1):20230187.
[19]	雷亚国, 韩天宇, 王彪, 等. XJTU-SY滚动轴承加速寿命试验数据集解读[J]. 机械工程学报, 2019, 55(16):1-6. doi: 10.3901/JME.2019.16.001
	LEI Y G, HAN T Y, WANG B, et al. XJTU-SY rolling element bearing accelerated life test datasets:a tutorial[J]. Journal of Mechanical Engineering, 2019, 55(16):1-6. (in Chinese)
[20]	颜家威, 易灿灿, 黄涛, 等. 基于CSPA-Informer的滚动轴承剩余寿命预测[J]. 组合机床与自动化加工技术, 2023(10):85-90.
	YAN J W, YI C C, HUANG T, et al. Research on remaining useful life prediction method of rolling bearings based on CSPA-Informer[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2023(10):85-90. (in Chinese)
[21]	葛阳, 郭兰中, 牛曙光, 等. 基于t-SNE和LSTM的旋转机械剩余寿命预测[J]. 振动与冲击, 2020, 39(7):223-231,273.
	GE Y, GUO L Z, NIU S G et al. Prediction of remaining useful life based on t-SNE and LSTM for rotating machinery[J]. Journal of Vibration and Shock, 2020, 39(7):223-231,273. (in Chinese)

工况编号	转速/rpm	径向力/kN
1	2100	12
2	2250	11
3	2400	10

工况编号	转速/rpm	径向力/kN
1	2100	12
2	2250	11
3	2400	10

工况编号	轴承编号	样本数量	实际寿命
1	Bearing 1_1	123	2h 3min
	Bearing 1_2	161	2h 41min
	Bearing 1_3	158	2h 38min
	Bearing 1_4	122	2h 2min
	Bearing 1_5	52	52min
2	Bearing 2_1	491	8h 11min
	Bearing 2_2	161	2h 41min
	Bearing 2_3	533	8h 53min
	Bearing 2_4	42	42min
	Bearing 2_5	339	5h 39min
3	Bearing 3_1	2538	42h 18min
	Bearing 3_2	2496	41h 36min
	Bearing 3_3	371	6h 11min
	Bearing 3_4	1515	25h 15min
	Bearing 3_5	114	1h 54min

工况编号	轴承编号	样本数量	实际寿命
1	Bearing 1_1	123	2h 3min
	Bearing 1_2	161	2h 41min
	Bearing 1_3	158	2h 38min
	Bearing 1_4	122	2h 2min
	Bearing 1_5	52	52min
2	Bearing 2_1	491	8h 11min
	Bearing 2_2	161	2h 41min
	Bearing 2_3	533	8h 53min
	Bearing 2_4	42	42min
	Bearing 2_5	339	5h 39min
3	Bearing 3_1	2538	42h 18min
	Bearing 3_2	2496	41h 36min
	Bearing 3_3	371	6h 11min
	Bearing 3_4	1515	25h 15min
	Bearing 3_5	114	1h 54min

工况编号	训练集	测试集
1	Bearing1_1，Bearing1_3， Bearing1_4，Bearing1_5	Bearing1_2
2	Bearing2_1，Bearing2_2， Bearing2_4，Bearing2_5	Bearing2_3
3	Bearing3_1，Bearing3_2， Bearing3_3，Bearing3_5	Bearing3_4