EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Research on a lead-acid battery fault detection method based on LSTM-AE-Cosine

Le Liu, Hongsheng Xu iD, Hai Tang, Jianing Cui, Li Feng, Ke Deng

PLOS One · 2026

DOI: 10.1371/journal.pone.0357237 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2026. Verfasst von Le Liu und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Intelligent Connected Vehicle, Hubei University of Automotive Technology, Shiyan, China. Hauptthemen laut MEDLINE: Electric Power Supplies, Lead, Equipment Failure Analysis. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Open Fund of the Shiyan Key Laboratory of Air-Ground Swarm Intelligence Coordination Technology and Applications, 2023 Hubei Provincial Key Research and Development Program Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Existing fault detection methods for lead-acid batteries in commercial vehicles are subject to several critical limitations, such as low detection accuracy and a shortage of labeled fault data. To address these issues, this paper presents an unsupervised deep learning framework for anomaly detection. In the framework, a hybrid LSTM-Autoencoder architecture is used to integrate the temporal feature extraction capability of long short-term memory networks with the reconstruction mechanism of Autoencoders, thus markedly improving the temporal modeling of battery data. Since the detection performance is highly dependent on the selection of reconstruction error metrics, multiple such metrics are employed in the model, and are systematically evaluated and compared to determine the most suitable metric for battery anomaly detection. The model is trained separately for static and driving conditions based on corresponding subsets of the battery datasets. With a fixed model structure and experimental conditions, model performance is evaluated using various reconstruction error metrics, and Bayesian optimization is used to identify the optimal detection threshold for each metric. Experimental results show that detection performance changes with different reconstruction error metrics and cosine similarity yields the best performance. This study offers a practical solution for online battery diagnosis and helps lower vehicle maintenance costs.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Electric Power SuppliesLeadEquipment Failure AnalysisLong Short Term MemoryAutoencoderBayes TheoremAlgorithms

Substanzen

Lead

Autor:innen und Institutionen

  • School of Intelligent Connected Vehicle, Hubei University of Automotive Technology, Shiyan, China.
  • Shiyan Key Laboratory of Air-Ground Crowd Cooperation Technology and Application (Hubei University of Automotive Technology), Hubei University of Automotive Technology, Shiyan, China.

ORCID-Profile: Hongsheng Xu

Förderung

  • Open Fund of the Shiyan Key Laboratory of Air-Ground Swarm Intelligence Coordination Technology and Applications
  • 2023 Hubei Provincial Key Research and Development Program Project

Zitieren

APA

Liu, L., Xu, H., Tang, H., Cui, J., Feng, L., & Deng, K. (2026). Research on a lead-acid battery fault detection method based on LSTM-AE-Cosine. PLOS One. https://doi.org/10.1371/journal.pone.0357237

Vancouver

Liu L, Xu H, Tang H, Cui J, Feng L, Deng K. Research on a lead-acid battery fault detection method based on LSTM-AE-Cosine. PLOS One. 2026. doi:10.1371/journal.pone.0357237

BibTeX
@article{Liu2026,
  author = {Liu, Le and Xu, Hongsheng and Tang, Hai and Cui, Jianing and Feng, Li and Deng, Ke},
  title = {Research on a lead-acid battery fault detection method based on LSTM-AE-Cosine},
  journal = {PLOS One},
  year = {2026},
  doi = {10.1371/journal.pone.0357237}
}
Kostenlos starten →