Fault Diagnosis of Lithium-Ion Battery Used in EV via K-Nearest Neighbor Algorithm

With the vigorous development of the electric vehicle industry, the research on fault diagnosis of lithium battery is crucial for the safe and stable operation of battery and the further development of battery technology. Due to the difficulty in obtaining actual operational fault data of lithium battery and the limited sample data, current research on lithium battery fault diagnosis is relatively difficult, and the diagnostic accuracy is often low. This study proposes a K-Nearest Neighbor-based lithium battery fault diagnosis method, which conducts fault diagnosis research on three types of lithium battery faults and compares the results obtained by other three algorithms. The experimental results prove that the average accuracy of K-Nearest Neighbor-based lithium battery fault classification is 97.98%, it is an effective fault diagnosis method.