Deep Learning-Enabled Fault Diagnosis of Lithium-Ion Batteries Using Real-World Vehicle Data With Gramian Angular Difference Fields

Battery failure represents one of the most common threats to electric vehicles (EVs). Existing diagnosis methods for onboard Lithium-ion batteries are heavily limited by complex real-world scenarios and struggle to handle early faults. With the aim of detecting battery faults in an early stage, this article proposes a deep learning-enabled fault diagnosis framework that blends the advantages of Gramian angular difference fields (GADF) and Transformer-based networks. First, a median-difference-process is developed to capture the dynamic electrical behaviors of cells. Then, the voltages of cells are converted into GADF matrices and presented as grayscale images. Afterward, a Vision Transformer is introduced to extract and learn the features of different battery fault patterns. Experimental verification in a real-world EV battery pack indicates that the proposed method achieves fault diagnosis for early battery failures with an accuracy of 97.30$\%$. Moreover, it outperforms existing methods and maintains a high recall rate of 94.77$\%$. Consequently, the proposed strategy proves to be effective for real-world applications.