Abstract

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.

IPC Classification

Keywords