Li- Ion Battery Life Cycle Estimation by KNN Algorithm

Precise estimation of the life cycle of Li-Ion batteries is a critical function of the Battery Management System (BMS). Among various approaches, data-driven methods are gaining prominence for State of Health ($\mathbf{(S O H})$ estimation due to their simplicity, suitability for real-time applications, and independence from complex battery models. This study proposes a machine learning based approach using the k-Nearest Neighbors (KNN) algorithm, which efficiently predicts battery life by analyzing charge-discharge sequences and their impact on battery degradation. The algorithm’s performance is evaluated using an open dataset, demonstrating its high accuracy in estimating battery SOH. Also, this research study explores the advantages and limitations of existing SOH estimation methods and highlights the potential of the proposed model for hybrid electric vehicle applications.