A Physics-Aware Attention LSTM Autoencoder for Early Fault Diagnosis of Battery Systems
This provides a robust solution for industrial battery management systems, addressing a critical safety challenge in electric vehicles, though it is incremental as it builds on existing deep learning methods with physics integration.
The paper tackles early fault diagnosis in battery systems for electric vehicles by proposing a Physics-Aware Attention LSTM Autoencoder, which integrates battery aging laws to address data-driven limitations; it improves recall by over 3 times while maintaining high precision on a real-world dataset.
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.