Comparative Analysis of Artificial Intelligence and Statistical Models for Li-ion Battery Cells State Estimation in Electric Vehicles

This study investigates the comparative performance of artificial intelligence (AI) and statistical models in estimating the state of lithium-ion (Li-ion) battery cells used in electric vehicles (EVs). The primary objective is to evaluate the accuracy and efficiency of different estimation techniques, facilitating better management of battery performance and longevity. The methodology involves a comprehensive analysis of existing AI algorithms, including neural networks and support vector machines, as well as classical statistical methods such as Kalman filters and regression models. Through systematic experimentation, data from various EV battery metrics are collected and analyzed to benchmark the predictive capabilities of these models. The results indicate that AI-driven approaches generally outperform traditional statistical techniques in terms of estimation accuracy, particularly under varying operational conditions. However, statistical models demonstrate greater reliability and lower computational requirements. This research contributes to the ongoing debate in battery management strategy, suggesting that a hybrid approach may offer the best balance between accuracy and efficiency. Further exploration is recommended to refine these models and assess their real-world applicability in the evolving landscape of electric vehicle technology.