Position Encoding Based Convolutional Neural Networks for Machine Remaining Useful Life Prediction

Page view(s)
11
Checked on Sep 21, 2022
Position Encoding Based Convolutional Neural Networks for Machine Remaining Useful Life Prediction
Title:
Position Encoding Based Convolutional Neural Networks for Machine Remaining Useful Life Prediction
Other Titles:
IEEE/CAA Journal of Automatica Sinica
Publication Date:
03 August 2022
Citation:
Jin, R., Wu, M., Wu, K., Gao, K., Chen, Z., & Li, X. (2022). Position Encoding Based Convolutional Neural Networks for Machine Remaining Useful Life Prediction. IEEE/CAA Journal of Automatica Sinica, 9(8), 1427–1439. https://doi.org/10.1109/jas.2022.105746
Abstract:
Accurate remaining useful life (RUL) prediction is important in industrial systems. It prevents machines from working under failure conditions, and ensures that the industrial system works reliably and efficiently. Recently, many deep learning based methods have been proposed to predict RUL. Among these methods, recurrent neural network (RNN) based approaches show a strong capability of capturing sequential information. This allows RNN based methods to perform better than convolutional neural network (CNN) based approaches on the RUL prediction task. In this paper, we question this common paradigm and argue that existing CNN based approaches are not designed according to the classic principles of CNN, which reduces their performances. Additionally, the capacity of capturing sequential information is highly affected by the receptive field of CNN, which is neglected by existing CNN based methods. To solve these problems, we propose a series of new CNNs, which show competitive results to RNN based methods. Compared with RNN, CNN processes the input signals in parallel so that the temporal sequence is not easily determined. To alleviate this issue, a position encoding scheme is developed to enhance the sequential information encoded by a CNN. Hence, our proposed position encoding based CNN called PE-Net is further improved and even performs better than RNN based methods. Extensive experiments are conducted on the C-MAPSS dataset, where our PE-Net shows state-of-the-art performance.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the National Research Foundation - AME Young Individual Research Grants (YIRG)
Grant Reference no. : A2084c0167
Description:
© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
2329-9266
2329-9274
Files uploaded:

Files uploaded:

File Size Format Action
pe-cnn.pdf 7.18 MB PDF Request a copy