EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A cross-domain deep learning framework for remaining useful life prediction in industrial applications

Sudip Saha, Muhammad Arslan Pervaiz, Muhammad Safwat Rahman, Rokibul Hasan, Ashifur Rahman iD

PLOS One · 31.07.2026 · 21 (7) · e0354721

DOI: 10.1371/journal.pone.0354721 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 31.07.2026. Verfasst von Sudip Saha und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Cyber-security, Pace University, New York, New York, United States of America. Hauptthemen laut MEDLINE: Deep Learning, Industry. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate prediction of Remaining Useful Life (RUL) is critical for predictive maintenance and minimizing downtime in industrial systems. This paper presents a cross-domain deep learning framework based on a hybrid Convolutional Neural Network–Bidirectional Long Short-Term Memory (CNN–BiLSTM) architecture. Unlike domain-specific models that require handcrafted features, the proposed framework extracts local degradation features through CNN layers and captures long-term dependencies via BiLSTM networks. The model is evaluated on three heterogeneous datasets: construction machinery, continuous casting machines, and lithium-ion batteries. Experimental results show that CNN–BiLSTM consistently outperforms baselines, achieving up to 22% lower RMSE compared to GRU and 30–50% lower RMSE compared to traditional models. On the construction dataset, it achieves an MAE of 48.2 hours and RMSE of 67.1 hours ( R 2 = 0.88), outperforming GRU by 20%. For the casting dataset, the model attains an MAE of 87.6 tons and RMSE of 113.9 tons ( R 2 = 0.87), surpassing Random Forest by over 35%. On the battery dataset, CNN–BiLSTM reduces the MAE to 49.6 cycles and RMSE to 72.8 cycles ( R 2 = 0.89), while also achieving the lowest Timeliness Score (27.5) and PHM08 Score (192.4). Cross-domain experiments are evaluated under two settings: zero-shot transfer, where the model is trained on one source domain and directly tested on a different target domain without using labeled target-domain samples, and fine-tuned transfer, where 20% of labeled target-domain samples are used to update only the fully connected layers while keeping the CNN and BiLSTM layers frozen. The zero-shot results reflect the effect of domain shift, while the fine-tuned results show that lightweight transfer adaptation reduces RMSE by 25–40% across domains. These findings indicate cross-domain adaptability under limited target-domain supervision rather than fully unsupervised cross-domain generalization. These results highlight the feasibility of a unified CNN–BiLSTM framework for scalable, cross-domain RUL estimation and its suitability for real-world prognostic applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningIndustryLong Short Term MemoryConvolutional Neural NetworksPrediction AlgorithmsPredictive Learning ModelsNeural Networks, Computer

Autor:innen und Institutionen

  • Department of Cyber-security, Pace University, New York, New York, United States of America.
  • Southeast Missouri State University, Cape Girardeau, Missouri, United States of America.
  • Department of CSE, Bangladesh University of Business and Technology, Dhaka, Bangladesh.

ORCID-Profile: Ashifur Rahman

Zitieren

APA

Saha, S., Pervaiz, M. A., Rahman, M. S., Hasan, R., & Rahman, A. (2026). A cross-domain deep learning framework for remaining useful life prediction in industrial applications. PLOS One, 21(7), e0354721. https://doi.org/10.1371/journal.pone.0354721

Vancouver

Saha S, Pervaiz MA, Rahman MS, Hasan R, Rahman A. A cross-domain deep learning framework for remaining useful life prediction in industrial applications. PLOS One. 2026;21(7):e0354721. doi:10.1371/journal.pone.0354721

BibTeX
@article{Saha2026,
  author = {Saha, Sudip and Pervaiz, Muhammad Arslan and Rahman, Muhammad Safwat and Hasan, Rokibul and Rahman, Ashifur},
  title = {A cross-domain deep learning framework for remaining useful life prediction in industrial applications},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {7},
  pages = {e0354721},
  doi = {10.1371/journal.pone.0354721}
}
Kostenlos starten →