EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

HybridoNet-Adapt: A domain-adapted framework for accurate lithium-ion battery RUL prediction

Khoa Tran iD, Bao Huynh, Tri Le, Lam Pham, Vy-Rin Nguyen, Duong Tran Anh, Hung-Cuong Trinh iD

PLOS One · 2025

DOI: 10.1371/journal.pone.0335066 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Khoa Tran und 6 weiteren Autor:innen. Beteiligte Einrichtung: AIWARE Limited Company, Da Nang, Vietnam. Hauptthemen laut MEDLINE: Lithium, Electric Power Supplies. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Đại học Tôn Đức Thắng.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate prediction of the Remaining Useful Life (RUL) of lithium-ion batteries is critical for safe, reliable Battery Health Management in diverse operating conditions. Existing RUL models often fail to generalize when test data diverge from the training distribution. To address this, we introduce HybridoNet-Adapt, a domain-adaptive RUL prediction framework that explicitly bridges the gap between labeled source and unlabeled target domains. During training, we minimize the Maximum Mean Discrepancy (MMD) between feature distributions to learn domain-invariant representations. Simultaneously, we employ two parallel predictors—one tailored to the source domain and one to the target domain—and balance their outputs via two learnable trade-off parameters, enabling the model to dynamically weight domain-specific insights. Our architecture couples this adaptation strategy with LSTM, multi-head attention, and Neural ODE blocks for deep temporal feature extraction, but its core novelty lies in the MMD-based alignment and hybrid prediction mechanism. On two large, publicly available battery datasets, HybridoNet-Adapt consistently outperforms non-adaptive baselines (Structural Pruning, Multi-Time Scale Feature Extraction Hybrid model, XGBoost, Elastic Net), archiving an RMSE reduction of up to 152 cycles under domain shifts. These results demonstrate that incorporating domain adaptation into RUL modeling substantially enhances robustness and real-world applicability.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

LithiumElectric Power SuppliesNeural Networks, ComputerAlgorithms

Substanzen

Lithium

Autor:innen und Institutionen

  • AIWARE Limited Company, Da Nang, Vietnam.
  • AIT Austrian Institute of Technology GmbH, Vienna, Austria.
  • Software Engineering Department, FPT University, Da Nang, Vietnam.
  • Laboratory of Environmental Sciences and Climate Change, Institute for Computational Science and Artificial Intelligence, Van Lang University, Ho Chi Minh City, Vietnam.
  • Faculty of Environment, Van Lang School of Technology, Van Lang University, Ho Chi Minh City, Vietnam.
  • Natural Language Processing and Knowledge Discovery Research Group, Faculty of Information Technology, Ton Duc Thang University, Ho Chi Minh City, Vietnam.

ORCID-Profile: Khoa Tran, Hung-Cuong Trinh

Förderung

  • Đại học Tôn Đức Thắng

Zitieren

APA

Tran, K., Huynh, B., Le, T., Pham, L., Nguyen, V. R., Tran Anh, D., & Trinh, H. C. (2025). HybridoNet-Adapt: A domain-adapted framework for accurate lithium-ion battery RUL prediction. PLOS One. https://doi.org/10.1371/journal.pone.0335066

Vancouver

Tran K, Huynh B, Le T, Pham L, Nguyen VR, Tran Anh D, et al. HybridoNet-Adapt: A domain-adapted framework for accurate lithium-ion battery RUL prediction. PLOS One. 2025. doi:10.1371/journal.pone.0335066

BibTeX
@article{Tran2025,
  author = {Tran, Khoa and Huynh, Bao and Le, Tri and Pham, Lam and Nguyen, Vy-Rin and Tran Anh, Duong and Trinh, Hung-Cuong},
  title = {HybridoNet-Adapt: A domain-adapted framework for accurate lithium-ion battery RUL prediction},
  journal = {PLOS One},
  year = {2025},
  doi = {10.1371/journal.pone.0335066}
}
Kostenlos starten →