IEICE TRANSACTIONS on Information
Bearing Remaining Useful Life Prediction Using 2D Attention Residual Network
Summary :
An attention residual network with triple feature as input is proposed to predict the remaining useful life (RUL) of bearings. First, the channel attention and spatial attention are connected in series into the residual connection of the residual neural network to obtain a new attention residual module, so that the newly constructed deep learning network can better pay attention to the weak changes of the bearing state. Secondly, the “triple feature” is used as the input of the attention residual network, so that the deep learning network can better grasp the change trend of bearing running state, and better realize the prediction of the RUL of bearing. Finally, The method is verified by a set of experimental data. The results show the method is simple and effective, has high prediction accuracy, and reduces manual intervention in RUL prediction.
- Publication
- IEICE TRANSACTIONS on Information Vol.E106-D No.5 pp.818-820
- Publication Date
- 2023/05/01
- Publicized
- 2022/05/27
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2022DLL0006
- Type of Manuscript
- Special Section LETTER (Special Section on Deep Learning Technologies: Architecture, Optimization, Techniques, and Applications)
- Category
- Smart Industry
Authors
Wenrong XIAO
Guizhou University of Engineering Science,China Three Gorges University
Yong CHEN
Guizhou University of Engineering Science,China Three Gorges University
Suqin GUO
Fujian Great Power Science and Technology Co., Ltd.
Kun CHEN
Fujian Great Power Science and Technology Co., Ltd.
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Wenrong XIAO, Yong CHEN, Suqin GUO, Kun CHEN, "Bearing Remaining Useful Life Prediction Using 2D Attention Residual Network" in IEICE TRANSACTIONS on Information,
vol. E106-D, no. 5, pp. 818-820, May 2023, doi: 10.1587/transinf.2022DLL0006.
Abstract: An attention residual network with triple feature as input is proposed to predict the remaining useful life (RUL) of bearings. First, the channel attention and spatial attention are connected in series into the residual connection of the residual neural network to obtain a new attention residual module, so that the newly constructed deep learning network can better pay attention to the weak changes of the bearing state. Secondly, the “triple feature” is used as the input of the attention residual network, so that the deep learning network can better grasp the change trend of bearing running state, and better realize the prediction of the RUL of bearing. Finally, The method is verified by a set of experimental data. The results show the method is simple and effective, has high prediction accuracy, and reduces manual intervention in RUL prediction.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022DLL0006/_p
Copy
@ARTICLE{e106-d_5_818,
author={Wenrong XIAO, Yong CHEN, Suqin GUO, Kun CHEN, },
journal={IEICE TRANSACTIONS on Information},
title={Bearing Remaining Useful Life Prediction Using 2D Attention Residual Network},
year={2023},
volume={E106-D},
number={5},
pages={818-820},
abstract={An attention residual network with triple feature as input is proposed to predict the remaining useful life (RUL) of bearings. First, the channel attention and spatial attention are connected in series into the residual connection of the residual neural network to obtain a new attention residual module, so that the newly constructed deep learning network can better pay attention to the weak changes of the bearing state. Secondly, the “triple feature” is used as the input of the attention residual network, so that the deep learning network can better grasp the change trend of bearing running state, and better realize the prediction of the RUL of bearing. Finally, The method is verified by a set of experimental data. The results show the method is simple and effective, has high prediction accuracy, and reduces manual intervention in RUL prediction.},
keywords={},
doi={10.1587/transinf.2022DLL0006},
ISSN={1745-1361},
month={May},}
Copy
TY - JOUR
TI - Bearing Remaining Useful Life Prediction Using 2D Attention Residual Network
T2 - IEICE TRANSACTIONS on Information
SP - 818
EP - 820
AU - Wenrong XIAO
AU - Yong CHEN
AU - Suqin GUO
AU - Kun CHEN
PY - 2023
DO - 10.1587/transinf.2022DLL0006
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2023
AB - An attention residual network with triple feature as input is proposed to predict the remaining useful life (RUL) of bearings. First, the channel attention and spatial attention are connected in series into the residual connection of the residual neural network to obtain a new attention residual module, so that the newly constructed deep learning network can better pay attention to the weak changes of the bearing state. Secondly, the “triple feature” is used as the input of the attention residual network, so that the deep learning network can better grasp the change trend of bearing running state, and better realize the prediction of the RUL of bearing. Finally, The method is verified by a set of experimental data. The results show the method is simple and effective, has high prediction accuracy, and reduces manual intervention in RUL prediction.
ER -
English
