EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Adaptive Framework for Remaining Useful Life Prediction Integrating Attention Mechanism and Deep Reinforcement Learning

Yanhui Bai iD, Jiajia Du, Honghui Li iD, Xintao Bao, Linjun Li, Chun Zhang iD, Jiahe Yan, Renliang Wang iD, Yi Xu

Sensors · 14.10.2025 · 25 (20) · 6354

DOI: 10.3390/s25206354 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 14.10.2025. Verfasst von Yanhui Bai und 8 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Beijing Jiaotong University, Beijing100044, China. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China National Energy Co., Ltd, China State Railway Group Co., Ltd.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The prediction of Remaining Useful Life (RUL) constitutes a vital aspect of Prognostics and Health Management (PHM), providing capabilities for the assessment of mechanical component health status and prediction of failure instances. Recent studies on feature extraction, time-series modeling, and multi-task learning have shown remarkable advancements. However, most deep learning (DL) techniques predominantly focus on unimodal data or static feature extraction techniques, resulting in a lack of RUL prediction methods that can effectively capture the individual differences among heterogeneous sensors and failure modes under complex operational conditions. To overcome these limitations, an adaptive RUL prediction framework named ADAPT-RULNet is proposed for mechanical components, integrating the feature extraction capabilities of attention-enhanced deep learning (DL) and the decision-making abilities of deep reinforcement learning (DRL) to achieve end-to-end optimization from raw data to accurate RUL prediction. Initially, Functional Alignment Resampling (FAR) is employed to generate high-quality functional signals; then, attention-enhanced Dynamic Time Warping (DTW) is leveraged to obtain individual degradation stages. Subsequently, an attention-enhanced of hybrid multi-scale RUL prediction network is constructed to extract both local and global features from multi-format data. Furthermore, the network achieves optimal feature representation by adaptively fusing multi-source features through Bayesian methods. Finally, we innovatively introduce a Deep Deterministic Policy Gradient (DDPG) strategy from DRL to adaptively optimize key parameters in the construction of individual degradation stages and achieve a global balance between model complexity and prediction accuracy. The proposed model was evaluated on aircraft engines and railway freight car wheels. The results indicate that it achieves a lower average Root Mean Square Error (RMSE) and higher accuracy in comparison with current approaches. Moreover, the method shows strong potential for improving prediction accuracy and robustness in varied industrial applications.

Schlagwörter

Stichwörter der Autor:innen

Deep Deterministic Policy Gradient (DDPG)Functional Alignment Resampling (FAR)attention mechanismremaining useful life (RUL) prediction

Autor:innen und Institutionen

  • School of Computer Science and Technology, Beijing Jiaotong University, Beijing100044, China.
  • Engineering Research Center of Network Management Technology for High Speed Railway, Ministry of Education, Beijing 100816, China.
  • China National Energy Co., Ltd., Beijing 100048, China.

ORCID-Profile: Yanhui Bai, Honghui Li, Chun Zhang, Renliang Wang

Förderung

  • China National Energy Co., Ltd
  • China State Railway Group Co., Ltd

Zitieren

APA

Bai, Y., Du, J., Li, H., Bao, X., Li, L., Zhang, C., Yan, J., Wang, R., & Xu, Y. (2025). An Adaptive Framework for Remaining Useful Life Prediction Integrating Attention Mechanism and Deep Reinforcement Learning. Sensors, 25(20), 6354. https://doi.org/10.3390/s25206354

Vancouver

Bai Y, Du J, Li H, Bao X, Li L, Zhang C, et al. An Adaptive Framework for Remaining Useful Life Prediction Integrating Attention Mechanism and Deep Reinforcement Learning. Sensors. 2025;25(20):6354. doi:10.3390/s25206354

BibTeX
@article{Bai2025,
  author = {Bai, Yanhui and Du, Jiajia and Li, Honghui and Bao, Xintao and Li, Linjun and Zhang, Chun and Yan, Jiahe and Wang, Renliang and Xu, Yi},
  title = {An Adaptive Framework for Remaining Useful Life Prediction Integrating Attention Mechanism and Deep Reinforcement Learning},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {20},
  pages = {6354},
  doi = {10.3390/s25206354}
}
Kostenlos starten →