An Early Multi-Fault Diagnosis Method of Lithium-ion Battery Based on Data-Driven

Lithium-ion power battery is the "heart" of electric vehicles. It is significant to diagnose the battery fault quickly and accurately. A real-time data driven diagnosis approach for early battery faults based on improved principal component analysis is proposed in this paper. The technique rotates the battery pack voltage sequence into a new coordinate space through linear combination, while the detection metrics of square prediction errors and modified contribution plots are employed to achieve minor fault traceability. In addition, the training sample of this method relies on the voltage sequence of the battery health state instead of the battery fault data which is difficult to collect. The experimental results demonstrate that this approach can not only locate the battery cell where the fault occurs, but also diagnose the open-circuit and short-circuit faults of the battery as well as the occurrence and duration of the fault in real-time. Furthermore, the feasibility and robustness of the proposed method are verified by applying different experimental data. In summary, the presented approach provides an easy-to-implement option that does not require accurate mathematical modeling, expert understanding, and complex computational processes.