Early Stage Internal Short Circuit Fault Diagnosis of Lithium-Ion Battery Pack Based on Improved Principal Component Analysis Method

In order to achieve the early stage diagnosis of internal short circuit faults (ISC) in lithium battery packs, this thesis proposes a fault diagnosis strategy based on Successive Variational Mode Decomposition (SVMD) combined with Principal Component Analysis (PCA). In this strategy, SVMD is used to extract the voltage fault features, the fault features are modeled online by PCA to obtain the SPE statistical control limit, and then the fault features are substituted into the PCA model to calculate the SPE statistics. By monitoring whether the SPE statistics exceed the control limit, the fault is judged to occur, and then the SPE contribution value of each battery is calculated to locate the faulty battery. The final experimental results show that the SVMD algorithm can simply and effectively extract fault features, and the PCA online integrated modeling and diagnosis can effectively avoid model mismatch and accurately locate the fault occurrence time, and the proposed method has a better effect on internal short circuit fault diagnosis in the early stage than the correlation coefficient method.