Remaining Useful Life Prediction for Aero-Engines Based on Multi-Scale Dilated Fusion Attention Model
Open Access
- 7 September 2025
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 15 (17) , 9813
Abstract
To address the limitations of CNNs and RNNs in handling complex operating conditions, multi-scale degradation patterns, and long-term dependencies—with attention mechanisms often failing to highlight key degradation features—this paper proposes a remaining useful life (RUL) prediction framework based on a multi-scale dilated fusion attention (MDFA) module. The MDFA leverages parallel dilated convolutions with varying dilation rates to expand receptive fields, while a global-pooling branch captures sequence-level degradation trends. Additionally, integrated channel and spatial attention mechanisms enhance the model’s ability to emphasize informative features and suppress noise, thereby improving overall prediction robustness. The proposed method is evaluated on NASA’s C-MAPSS and N-CMAPSS datasets, achieving MAE values of 0.018–0.026, RMSE values of 0.021–0.032, and R2 scores above 0.987, demonstrating superior accuracy and stability compared to existing baselines. Furthermore, to verify generalization across domains, experiments on the PHM2012 bearing dataset show similar performance (MAE: 0.023–0.026, RMSE: 0.031–0.032, R2: 0.987–0.995), confirming the model’s effectiveness under diverse operating conditions and its adaptability to different degradation behaviors. This study provides a practical and interpretable deep-learning solution for RUL prediction, with broad applicability to aero-engine prognostics and other industrial health-monitoring tasks.Keywords
This publication has 29 references indexed in Scilit:
- MSDANet: A multi-scale dilation attention network for medical image segmentationBiomedical Signal Processing and Control, 2023
- Remaining useful life prediction of weighted k-out-of-n systems based on dynamic random weights of importanceComputers & Industrial Engineering, 2023
- Multi-scale attention-based lightweight network with dilated convolutions for infrared and visible image fusionComplex & Intelligent Systems, 2023
- Self-Attention Transformer-Based Architecture for Remaining Useful Life Estimation of Complex MachinesProcedia Computer Science, 2023
- Trend attention fully convolutional network for remaining useful life estimationReliability Engineering & System Safety, 2022
- Prediction of remaining useful life based on bidirectional gated recurrent unit with temporal self-attention mechanismReliability Engineering & System Safety, 2022
- State-of-charge estimation and remaining useful life prediction of supercapacitorsRenewable and Sustainable Energy Reviews, 2021
- Fatigue life prediction of aero-engine compressor disk based on a new stress field intensity approachInternational Journal of Mechanical Sciences, 2020
- Remaining useful life estimation in prognostics using deep convolution neural networksReliability Engineering & System Safety, 2018
- Formalisation of a new prognosis model for supporting proactive maintenance implementation on industrial systemReliability Engineering & System Safety, 2008