Research on Prediction of Model Based on Multi-scale LSTM

Authors

Junjie Qiu, School of Information Science and Engineering, East Chines of Science and Technology, Shanghai 200237, China;Follow
Hong Zheng, School of Information Science and Engineering, East Chines of Science and Technology, Shanghai 200237, China;Follow
Yunhui Cheng, School of Information Science and Engineering, East Chines of Science and Technology, Shanghai 200237, China;

Abstract

Abstract: Aircraft engine remaining useful life (RUL) prediction is the core issue in equipmentfailure prognostics and health management (PHM). Aiming at the characteristics of high dimensionality, high lag and complexity of engine data, a multi-scale attention-based bidirectional long short-term memory neural network model based on self-training weights is proposed. Multi-scale features are extracted through bidirectional long short-term memory neural network (BiLSTM) of different scales. A fusion algorithm based on self-training weights is proposed, and an attention mechanism is introduced to screen features at different scales to improve prediction accuracy. Various models are compared on the NASA's C-MAPSS data set. The results prove that the proposed prediction model improves in both accuracy and root mean square error indicators.

Recommended Citation

Qiu, Junjie; Zheng, Hong; and Cheng, Yunhui (2022) "Research on Prediction of Model Based on Multi-scale LSTM," Journal of System Simulation: Vol. 34: Iss. 7, Article 20.
DOI: 10.16182/j.issn1004731x.joss.21-0182
Available at: https://dc-china-simulation.researchcommons.org/journal/vol34/iss7/20

First Page

1593

Revised Date

2021-06-24

DOI Link

https://doi.org/10.16182/j.issn1004731x.joss.21-0182

Last Page

1604

CLC

TP391.9

Recommended Citation

Junjie Qiu, Hong Zheng, Yunhui Cheng. Research on Prediction of Model Based on Multi-scale LSTM[J]. Journal of System Simulation, 2022, 34(7): 1593-1604.

Corresponding Author

Hong Zheng,zhenghong@ecust.edu.cn

DOI

10.16182/j.issn1004731x.joss.21-0182