SACGNet: A Remaining Useful Life Prediction of Bearing with Self-Attention Augmented Convolution GRU Network

被引:9
|
作者
Xu, Juan [1 ]
Duan, Shiyu [1 ]
Chen, Weiwei [2 ]
Wang, Dongfeng [3 ]
Fan, Yuqi [4 ]
机构
[1] Hefei Univ Technol, Sch Comp Sci & Informat Engn, Key Lab Knowledge Engn Big Data, Hefei 230009, Peoples R China
[2] Shanghai Aerosp Control Technol Inst, Shanghai 201109, Peoples R China
[3] Luoyang Bearing Res Inst Co Ltd, Luoyang 471033, Peoples R China
[4] Hefei Univ Technol, Sch Comp & Informat, Hefei 230009, Peoples R China
关键词
self-attention; gated neural network; remaining useful life prediction; health indicator; CLASSIFICATION; PROGNOSTICS; UNIT;
D O I
10.3390/lubricants10020021
中图分类号
TH [机械、仪表工业];
学科分类号
0802 ;
摘要
In recent years, the development of deep learning-based remaining useful life (RUL) prediction methods of bearings has flourished because of their high accuracy, easy implementation, and lack of reliance on a priori knowledge. However, there are two challenging issues concerning the prediction accuracy of existing methods. The run-to-failure sequential data and its RUL labels are almost inaccessible in real-world scenarios. Meanwhile, the existing models usually capture the general degradation trend of bearings while ignoring the local information, which restricts the model performance. To tackle the aforementioned problems, we propose a novel health indicator derived from the original vibration signals by combining principal components analysis with Euclidean distance metric, which was motivated by the desire to resolve the dependency on RUL labels. Then, we design a novel self-attention augmented convolution GRU network (SACGNet) to predict the RUL. Combining a self-attention mechanism with a convolution framework can both adaptively assign greater weights to more important information and focus on local information. Furthermore, Gated Recurrent Units are used to parse the long-term dependencies in weighted features such that SACGNet can utilize the important weighted features and focus on local features to improve the prognostic accuracy. The experimental results on the PHM 2012 Challenge dataset and the XJTU-SY bearing dataset have demonstrated that our proposed method is superior to the state of the art.
引用
收藏
页数:18
相关论文
共 50 条
  • [1] Remaining useful life prediction of bearings based on self-attention mechanism, multi-scale dilated causal convolution, and temporal convolution network
    Wei, Hao
    Zhang, Qinghua
    Gu, Yu
    [J]. MEASUREMENT SCIENCE AND TECHNOLOGY, 2023, 34 (04)
  • [2] Prediction of Bearing Remaining Useful Life With Deep Convolution Neural Network
    Ren, Lei
    Sun, Yaqiang
    Wang, Hao
    Zhang, Lin
    [J]. IEEE ACCESS, 2018, 6 : 13041 - 13049
  • [3] Improved GRU-based self-attention optimization algorithm for aero-engine remaining useful life prediction
    Guo, Xiaojing
    Xu, Xiaohui
    Guo, Jiahao
    [J]. Hangkong Dongli Xuebao/Journal of Aerospace Power, 2024, 39 (12):
  • [4] Machine remaining life prediction based on multi-layer self-attention and temporal convolution network
    Shang, Zhiwu
    Zhang, Baoren
    Li, Wanxiang
    Qian, Shiqi
    Zhang, Jie
    [J]. COMPLEX & INTELLIGENT SYSTEMS, 2022, 8 (02) : 1409 - 1424
  • [5] Machine remaining life prediction based on multi-layer self-attention and temporal convolution network
    Zhiwu Shang
    Baoren Zhang
    Wanxiang Li
    Shiqi Qian
    Jie Zhang
    [J]. Complex & Intelligent Systems, 2022, 8 : 1409 - 1424
  • [6] Remaining Useful Life Prediction of Bearings Based on Convolution Attention Mechanism and Temporal Convolution Network
    Wang, Haitao
    Yang, Jie
    Wang, Ruihua
    Shi, Lichen
    [J]. IEEE ACCESS, 2023, 11 : 24407 - 24419
  • [7] Bearing remaining useful life prediction using self-adaptive graph convolutional networks with self-attention mechanism
    Wei, Yupeng
    Wu, Dazhong
    Terpenny, Janis
    [J]. MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2023, 188
  • [8] An integrated multi-head dual sparse self-attention network for remaining useful life prediction
    Zhang, Jiusi
    Li, Xiang
    Tian, Jilun
    Luo, Hao
    Yin, Shen
    [J]. RELIABILITY ENGINEERING & SYSTEM SAFETY, 2023, 233
  • [9] Remaining Useful Life Prediction Using Temporal Convolution with Attention
    Tan, Wei Ming
    Teo, T. Hui
    [J]. AI, 2021, 2 (01) : 48 - 70
  • [10] Temporal Convolutional Network with Attention Mechanism for Bearing Remaining Useful Life Prediction
    Wang, Shuai
    Zhang, Chao
    Lv, Da
    Zhao, Wentao
    [J]. PROCEEDINGS OF TEPEN 2022, 2023, 129 : 391 - 400