EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Early and Uncertainty-Aware Detection of Impending Voltage Outliers in Battery Packs via a Probabilistic Hierarchical Adaptive Framework

Teng Liu, Wei Li, Zhiqiang Li, Shangbo Wu

Batteries · 06.07.2026 · 12 (7) · 245

DOI: 10.3390/batteries12070245 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Batteries, online erschienen am 06.07.2026. Verfasst von Teng Liu und 3 weiteren Autor:innen. Die Arbeit nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Open Fund Project of Vehicle Measurement, Control and Safety Key Laboratory of Sichuan Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The global adoption of electric vehicles (EVs) highlights the critical role of lithium-ion battery packs in ensuring safety and performance, while voltage outliers as precursors to thermal runaway pose significant risks. Existing fault detection methods suffer from limited adaptability, poor uncertainty quantification, and inadequate handling of long-term temporal dynamics. To address these gaps, this study proposes a Probabilistic Hierarchical Adaptive Framework (PHAF) for early, uncertainty-aware detection of impending voltage outliers. PHAF integrates three core innovations: (1) the Weighted Outlier Depth (WOD) metric, which fuses Boltzmann-weighted voltage deviations and gradient-based thermal penalties to sensitively capture electro-thermal anomalies, especially under thermal stress (>45 °C); (2) the Learnable Spectral Convolution Network (LSCN), a novel architecture that combines adaptive spectral modulation and dual-path convolutions to model long-range frequency patterns and local temporal dependencies in voltage sequences; and (3) a hierarchical multi-model system that dynamically selects specialized models (LSCN, GRU, and LSTM) across four prediction horizons (160–40 min), leveraging quantile regression for uncertainty quantification and an early-termination mechanism to optimize computational efficiency. Evaluated on real-world data from 60 AITO EVs, PHAF achieves 95.4% classification accuracy for Level 1 (early-stage) faults at the 160 min horizon, >90% accuracy for critical Level 3 faults within 80 min, and a maximum AUC of 0.943 for long-term anomaly detection. This framework enables a transition from passive remediation to active prevention of battery thermal runaway, providing reliable, confidence-aware monitoring for safety-critical EV applications.

Förderung

  • the Open Fund Project of Vehicle Measurement, Control and Safety Key Laboratory of Sichuan Province

Zitieren

APA

Liu, T., Li, W., Li, Z., & Wu, S. (2026). Early and Uncertainty-Aware Detection of Impending Voltage Outliers in Battery Packs via a Probabilistic Hierarchical Adaptive Framework. Batteries, 12(7), 245. https://doi.org/10.3390/batteries12070245

Vancouver

Liu T, Li W, Li Z, Wu S. Early and Uncertainty-Aware Detection of Impending Voltage Outliers in Battery Packs via a Probabilistic Hierarchical Adaptive Framework. Batteries. 2026;12(7):245. doi:10.3390/batteries12070245

BibTeX
@article{Liu2026,
  author = {Liu, Teng and Li, Wei and Li, Zhiqiang and Wu, Shangbo},
  title = {Early and Uncertainty-Aware Detection of Impending Voltage Outliers in Battery Packs via a Probabilistic Hierarchical Adaptive Framework},
  journal = {Batteries},
  year = {2026},
  volume = {12},
  number = {7},
  pages = {245},
  doi = {10.3390/batteries12070245}
}
Kostenlos starten →