Associations of battery cell voltage consistency with driving behavior of real-world electric vehicles

For proposing an adaptive-threshold-based method for detecting battery voltage inconsistency fault, this study explored the associations between driving behavior and voltage consistency between cells (VCC) at a microscopic level, by performing a naturalistic driving experiment on real-world electric vehicles (EVs). The running process of EVs is divided into four kinds of micro-segments A, B, C, D through the driver's pedal actions. Focusing on these segments, Pearson correlation coefficients (PCCs) between driving behavior parameters (DBPs) and voltage variation coefficient between cells (VVCC) are calculated, the impact patterns of DBPs to VVCC are analyzed by accumulated local effects (ALE) plots obtained from random forest (RF) modeling. The results show that the maximum PCC is reached by average accelerator pedal stroke with 0.724 for segments A, and by average speed with 0.789, 0.554, and 0.553 for the other three segments. The four RF models show a high accuracy of VVCC prediction with goodness of fit over 0.919, and the ALE plots demonstrate the impact patterns are positive-nonlinear overall. The maximum VVCC growing rates are reached by average accelerator pedal stroke for segments A (48.09%), and average speed for other segments (55.70%, 29.01%, and 23.68% for segments B, C, and D, respectively). These results imply a strong connection between driving behavior and battery voltage consistency, which could be effectively captured to provide crucial inputs and interpretation methods for modeling voltage consistency prediction during EVs running. Hence, this work lays the foundation for the development of battery voltage fault detection algorithms considering different driving states.