Abstract:

The increasing demand for electric vehicles (EVs) has driven advancements in powertrain technology to enhance efficiency, performance, and sustainability. A key component of this evolution is the Battery Management System (BMS), responsible for optimizing battery performance,ensuring safety, and extending battery lifespan. The study compares several machine learning algorithms for SOC and SOH estimation, identifying artificial neural network (ANN) and long-short term memory (LSTM) as the most effective methods due to their ability to handle the nonlinear behavior of Li-ion (Li-ion) batteries. The integration of BMS with other powertraincomponents, such as the inverter and motor, is also discussed, emphasizing the role of BMS in optimizing energy flow and ensuring seamless system interaction.This thesis outlines a comprehensive approach to designing an efficient EV powertrain by optimizing the BMS, with a focus on energy management, state estimation, and cell balancing.