Remaining Useful Life Prediction of Rolling Bearings Based on Policy Gradient Informer Model

被引:0
|
作者
Xiong, Jiahao [1 ]
Li, Feng [1 ]
Tang, Baoping [2 ]
Wang, Yongchao [1 ]
Luo, Ling [3 ]
机构
[1] School of Mechanical Eng., Sichuan Univ., Chengdu,610065, China
[2] State Key Lab. of Mechanical Transmissions, Chongqing Univ., Chongqing,400044, China
[3] National Inst. of Measurement and Testing Technol., Chengdu,610021, China
来源
Gongcheng Kexue Yu Jishu/Advanced Engineering Sciences | 2024年 / 56卷 / 04期
关键词
Computational efficiency - Decoding - Distillation - Encoding (symbols) - Memory architecture - Roller bearings - Signal encoding - Time series;
D O I
10.12454/j.jsuese.202300136
中图分类号
学科分类号
摘要
As a typical encoder–decoder, the transformer architecture has inherent limitations such as secondary time complexity, high memory usage, and a complex model structure; these issues can lead to lower prediction accuracy and decreased computational efficiency when applied to the prediction of the remaining useful life (RUL) of rolling bearings. For this reason, herein, a novel encoder–decoder, the Policy Gradient Informer (PG–Informer) model, is proposed and applied to the prediction of the RUL of rolling bearings for the first time. First, in the new encoder–decoder architecture of PG–Informer, a probabilistic sparse self-attention m echanism is used to replace the original self-attention mechanism of the transformer architecture to improve its nonlinear approximation ability and reduce its time and space complexity. Then, the self-attention distillation operation is used to reduce its number of parameters and their dimensions and enhance the prediction robustness of time series. Moreover, the generative decoder of PG–Informer only needs to decode the decoding input in one step to output the prediction results without dynamic multistep decoding, which improves the prediction speed of time series. Finally, a policy-gradient learning algorithm is constructed to improve the training speed of the PG–Informer parameters. These advantages enable the proposed rolling-bearing RUL-prediction method to obtain higher prediction accuracy, better robustness, and higher computational efficiency. Results for the No. 1 rolling bearing at the Center for Intelligent Maintenance Systems of the University of Cincinnati show that the proposed method was able to predict an RUL value of 963 min, representing a prediction error of only 6.50% when compared to the experimental result; compared to the transformer-based RUL prediction method, this represents a higher prediction accuracy, a smaller prediction error, and greater robustness. The proposed method consumed only 132.37 s for RUL prediction, shorter than the time taken by the transformer-based RUL-prediction method. These results verify the effectiveness and advantages of the proposed method. © 2024 Sichuan University. All rights reserved.
引用
收藏
页码:273 / 286
相关论文
共 50 条
  • [31] CNN-LSTM-Based Model for Predicting the Remaining Useful Life of Rolling Bearings
    Yu, Xiaopeng
    Zhang, Hao
    Zhao, Fukai
    Zhen, Dong
    Lu, Kiuhua
    Hu, Wei
    PROCEEDINGS OF TEPEN 2022, 2023, 129 : 354 - 366
  • [32] Remaining Useful Life Prediction Method for Rolling Bearings Based on CBAM-CNN-BiLSTM
    Zhou, Honggen
    Ren, Xiaodie
    Sun, Li
    Li, Guochao
    Liu, Yinfei
    2023 IEEE 12TH DATA DRIVEN CONTROL AND LEARNING SYSTEMS CONFERENCE, DDCLS, 2023, : 147 - 154
  • [33] Remaining useful life prediction method for rolling bearings based on hybrid dilated convolution transfer
    Zhang, Bo
    Hu, Changhua
    Zhang, Hao
    Zheng, Jianfei
    Zhang, Jianxun
    Pei, Hong
    QUALITY AND RELIABILITY ENGINEERING INTERNATIONAL, 2024, 40 (06) : 3018 - 3036
  • [34] Remaining useful life prediction of rolling bearings based on Bayesian neural network and uncertainty quantification
    Jiang, Guang-Jun
    Yang, Jin-Sen
    Cheng, Tian-Cai
    Sun, Hong-Hua
    QUALITY AND RELIABILITY ENGINEERING INTERNATIONAL, 2023, 39 (05) : 1756 - 1774
  • [35] Research on remaining useful life prediction methods for rolling bearings based on a novel gated unit
    Ma, Ke
    Huang, Weiguo
    Ding, Chuancang
    Shi, Juanjuan
    Wang, Jun
    Shen, Changqing
    Jiang, Xingxing
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2024, 35 (11)
  • [36] Remaining Useful Life prediction of rolling bearings based on risk assessment and degradation state coefficient
    Li, Qiang
    Yan, Changfeng
    Chen, Guangyi
    Wang, Huibin
    Li, Hongkun
    Wu, Lixiao
    ISA TRANSACTIONS, 2022, 129 : 413 - 428
  • [37] Remaining useful life prediction of rolling element bearings based on simulated performance degradation dictionary
    Cui, Lingli
    Wang, Xin
    Wang, Huaqing
    Jiang, Hong
    MECHANISM AND MACHINE THEORY, 2020, 153
  • [38] Remaining useful life prediction of rolling bearings based on time convolutional network and transformer in parallel
    Tang, Youfu
    Liu, Ruifeng
    Li, Chunhui
    Lei, Na
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2024, 35 (12)
  • [39] Remaining useful life prediction for rolling bearings based on adaptive aggregation of dynamic feature correlations
    Sun, Sichao
    Luo, Jie
    Huang, Ao
    Xia, Xinyu
    Yang, Jiale
    Zhou, Hua
    JOURNAL OF VIBRATION AND CONTROL, 2024,
  • [40] Remaining useful life prediction of rolling bearings based on dual Channel regression fusion network
    Xu, Hao
    Gao, Qian
    Wang, Mingbang
    Lu, Chengxing
    Yang, Zhibo
    Chen, Jian
    Zhendong yu Chongji/Journal of Vibration and Shock, 2025, 44 (04): : 322 - 332