A Physics-Aware Attention LSTM Autoencoder for Early Fault Diagnosis of Battery Systems

TL;DR

This paper introduces a physics-aware attention LSTM autoencoder that enhances early fault detection in batteries by integrating aging laws into deep learning, significantly improving recall rates over existing methods.

Contribution

The paper presents a novel framework that explicitly incorporates battery aging physics into deep learning for early fault diagnosis, addressing limitations of previous data-driven approaches.

Findings

Over 3 times improvement in early fault recall rate

Outperforms state-of-the-art baselines on real-world data

Maintains high precision in fault detection

Abstract

Battery safety is paramount for electric vehicles. Early fault diagnosis remains a challenge due to the subtle nature of anomalies and the interference of dynamic operating noise. Existing data-driven methods often suffer from "physical blindness" leading to missed detections or false alarms. To address this, we propose a Physics-Aware Attention LSTM Autoencoder (PA-ALSTM-AE). This novel framework explicitly integrates battery aging laws (mileage) into the deep learning pipeline through a multi-stage fusion mechanism. Specifically, an adaptive physical feature construction module selects mileage-sensitive features, and a physics-guided latent fusion module dynamically calibrates the memory cells of the LSTM based on the aging state. Extensive experiments on the large-scale Vloong real-world dataset demonstrate that the proposed method significantly outperforms state-of-the-art baselines. Notably, it improves the recall rate of early faults by over 3 times while maintaining high precision, offering a robust solution for industrial battery management systems.