Inconsistency Diagnosis of Power Batteries Based on End-Cloud Collaboration

In electric vehicles, power batteries consist of numerous individual cells connected in series or parallel. Variations in manufacturing, operating conditions, and aging can lead to differences among these cells. Such inconsistencies can compromise the battery pack’s performance, safety, and overall service life. Therefore, accurately diagnosing inconsistencies among battery cells is of great significance for enhancing the reliability of the battery system and ensuring the operational safety of the vehicle. To address the limited computational resources available in vehicles, this paper proposes an end-cloud collaborative fault diagnosis framework and validates its effectiveness using real-world vehicle driving data. On the cloud side, a deep learning-based reconstruction network is developed to enable high-precision reconstruction of cell voltages. On the vehicle side, a second-order equivalent circuit model is used to represent battery dynamics. An adaptive forgetting factor recursive least squares method is introduced for online estimation of the model parameters, enabling accurate local prediction of individual cell voltages. Using the cloud-reconstructed and vehicle-predicted cell voltages, the extreme difference value of voltage for each cell is computed. A comprehensive diagnosis of inconsistency faults is then performed by fusing the extreme difference in voltage results from both the cloud and vehicle sides via the Extended Kalman Filter (EKF); threshold judgment is conducted based on the fused results, and the Cumulative Sum (CUSUM) algorithm is designed to identify cell inconsistency faults. Experimental results show that the proposed method effectively detects battery inconsistency faults and demonstrates strong engineering applicability and practical potential.