The Impact of Battery Cell Configuration on Electric Vehicle Performance: An XGBoost-Based Classification with SHAP Interpretability

TL;DR

This paper develops an XGBoost-based machine learning model to classify EV acceleration performance and uses SHAP to interpret how battery configuration impacts vehicle performance, revealing complex non-linear relationships.

Contribution

It introduces a novel ML framework combining XGBoost and SHAP for analyzing the effect of battery configuration on EV performance, addressing gaps in existing literature.

Findings

Battery cell count initially improves power but eventually hampers performance due to increased mass and complexity.

The model achieved 87.5% accuracy and high ROC-AUC, demonstrating effective classification.

Battery configuration must balance system complexity and design for optimal EV performance.

Abstract

As the electric vehicle (EV) market continues to prioritize dynamic performance and rapid charging, battery configuration has rapidly evolved. Despite this, current literature has often overlooked the complex, non-linear relationship between battery configuration and electric vehicle performance. To address this gap, this study proposes a machine learning framework which categorizes the EV acceleration performance into High (<= 4.0 seconds), Mid (4.0 - 7.0 seconds), and Low (> 7.0 seconds). Utilizing a preprocessed dataset consisting of 276 EV samples, an Extreme Gradient Boosting (XGBoost) classifier was utilized, achieving 87.5% predictive accuracy, a 0.968 ROC-AUC, and a 0.812 MCC. In order to ensure engineering transparency SHapley Additive exPlanations (SHAP) were employed. Results of analysis shows that an increase in battery cell count initially boosts power delivery, but its mass and complexity diminished performance gains eventually. As such, these findings indicate that battery configuration in EVs must balance system complexity and architectural configuration in order to receive and retain optimal vehicle performance.