During the operation of lithium-ion battery packs, there often exhibit certain abnormalities due to cell faults such as internal short circuit or unavoidable inconsistencies among cells, which affects the operation safety of the battery packs. Therefore, it is of great significance to carry out abnormality detection for the battery packs. Accordingly, this paper proposes a feature selection method based on Kullback-Leibler (K-L) test and an improved Greenwald-Khanna (GK) clustering algorithm. Initially, faults are introduced into the battery pack using the Simulink simulation platform to obtain simulation data. Subsequently, parameter identification is identified based on the Rint equivalent circuit model and the Recursive Least Squares (RLS) algorithm. Finally, better consistency features are selected using the K-L test as inputs to the GK clustering algorithm, and the K-Means++ method is used to optimize the GK algorithm for clustering features. The results demonstrate that this method can effectively distinguish between normal and abnormal batteries, achieving abnormality detection in battery packs.