A Method for Predicting the Remaining Life of Rolling Bearings Based on Multi-Scale Feature Extraction and Attention Mechanism

被引:11
作者
Jiang, Changhong [1 ]
Liu, Xinyu [1 ]
Liu, Yizheng [2 ]
Xie, Mujun [1 ]
Liang, Chao [1 ]
Wang, Qiming [1 ]
机构
[1] Changchun Univ Technol, Sch Elect & Elect Engn, Changchun 130000, Peoples R China
[2] Jilin Prov Dengxi Technol Co Ltd, Changchun 130022, Peoples R China
关键词
rolling bearing; residual life prediction; multi-scale feature extraction; attention mechanism; CONVOLUTIONAL NEURAL-NETWORK; RECOGNITION;
D O I
10.3390/electronics11213616
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In response to the problems of difficult identification of degradation stage start points and inadequate extraction of degradation features in the current rolling bearing remaining life prediction method, a rolling bearing remaining life prediction method based on multi-scale feature extraction and attention mechanism is proposed. Firstly, this paper takes the normalized bearing vibration signal as input and adopts a quadratic function as the RUL prediction label, avoiding identifying the degradation stage start point. Secondly, the spatial and temporal features of the bearing vibration signal are extracted using the dilated convolutional neural network and LSTM network, respectively, and the channel attention mechanism is used to assign weights to each degradation feature to effectively use multi-scale information. Finally, the mapping of bearing degradation features to remaining life labels is achieved through a fully connected layer for the RUL prediction of bearings. The proposed method is validated using the PHM 2012 Challenge bearing dataset, and the experimental results show that the predictive performance of the proposed method is superior to that of other RUL prediction methods.
引用
收藏
页数:16
相关论文
共 31 条
[1]   Prediction of Machine Health Condition Using Neuro-Fuzzy and Bayesian Algorithms [J].
Chen, Chaochao ;
Zhang, Bin ;
Vachtsevanos, George .
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2012, 61 (02) :297-306
[2]   An Improved Fault Diagnosis Using 1D-Convolutional Neural Network Model [J].
Chen, Chih-Cheng ;
Liu, Zhen ;
Yang, Guangsong ;
Wu, Chia-Chun ;
Ye, Qiubo .
ELECTRONICS, 2021, 10 (01) :1-19
[3]   A novel deep learning method based on attention mechanism for bearing remaining useful life prediction [J].
Chen, Yuanhang ;
Peng, Gaoliang ;
Zhu, Zhiyu ;
Li, Sijue .
APPLIED SOFT COMPUTING, 2020, 86
[4]   Fine-grained attention mechanism for neural machine translation [J].
Choi, Heeyoul ;
Cho, Kyunghyun ;
Bengio, Yoshua .
NEUROCOMPUTING, 2018, 284 :171-176
[5]   Research on Upper Limb Action Intention Recognition Method Based on Fusion of Posture Information and Visual Information [J].
Cui, Jian-Wei ;
Du, Han ;
Yan, Bing-Yan ;
Wang, Xuan-Jie .
ELECTRONICS, 2022, 11 (19)
[6]   DWT-LSTM-Based Fault Diagnosis of Rolling Bearings with Multi-Sensors [J].
Gu, Kai ;
Zhang, Yu ;
Liu, Xiaobo ;
Li, Heng ;
Ren, Mifeng .
ELECTRONICS, 2021, 10 (17)
[7]   Machinery health indicator construction based on convolutional neural networks considering trend burr [J].
Guo, Liang ;
Lei, Yaguo ;
Li, Naipeng ;
Yan, Tao ;
Li, Ningbo .
NEUROCOMPUTING, 2018, 292 :142-150
[8]   A recurrent neural network based health indicator for remaining useful life prediction of bearings [J].
Guo, Liang ;
Li, Naipeng ;
Jia, Feng ;
Lei, Yaguo ;
Lin, Jing .
NEUROCOMPUTING, 2017, 240 :98-109
[9]   Remaining Useful Life Prediction for Rolling Bearings Using EMD-RISI-LSTM [J].
Guo, Runxia ;
Wang, Yu ;
Zhang, Haochi ;
Zhang, Guoliang .
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2021, 70
[10]   Quantum weighted long short-term memory neural network and its application in state degradation trend prediction of rotating machinery [J].
Li, Feng ;
Xiang, Wang ;
Wang, Jiaxu ;
Zhou, Xueming ;
Tang, Baoping .
NEURAL NETWORKS, 2018, 106 :237-248