Attention-based Gate Recurrent Unit for remaining useful life prediction in prognostics

An essential process in prognostics and health management (PHM) is remaining useful life (RUL) prediction. The traditional Recurrent Neural Networks (RNNs) and their variants are not very efficient at solving the regression problems of RUL prediction. Given this problem, an attention-based Gate Recu...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Applied soft computing Ročník 143; s. 110419
Hlavní autori: Lin, Ruiguan, Wang, Huawei, Xiong, Minglan, Hou, Zhaoguo, Che, Changchang
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier B.V 01.08.2023
Predmet:
Attention
Encoder–decoder
Gate Recurrent Unit
Prognostics
Remaining useful life prediction
Encoder–decoder
Remaining useful life prediction
Gate Recurrent Unit
Prognostics
Attention
ISSN:1568-4946
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:An essential process in prognostics and health management (PHM) is remaining useful life (RUL) prediction. The traditional Recurrent Neural Networks (RNNs) and their variants are not very efficient at solving the regression problems of RUL prediction. Given this problem, an attention-based Gate Recurrent Unit (ABGRU) for RUL prediction is proposed in this paper. Firstly, the dataset is preprocessed, and the RUL labels are modeled using the piecewise linear degradation method. Then, a GRU network based on an encoder–decoder framework with an attention mechanism is proposed. The network can assign weights according to the importance of feature information and effectively use the feature information to predict RUL. The validity of the proposed framework is verified in the NASA C-MAPSS benchmark dataset. The results show that the presented method outperforms the existing state-of-the-art approaches and provides a new solution for RUL Prediction. •Propose a novel method for RUL predictions based on an attention-based GRU.•Construct an Encoder–Decoder model that integrates GRU.•The attention assigns weights and uses the feature information effectively.•Comparisons with state-of-the-art verify the superiority of the proposed method.
ISSN:1568-4946
DOI:10.1016/j.asoc.2023.110419