Abstract
The ongoing global transition toward sustainable, electrified mobility relies almost entirely on the rapid development, optimization, and implementation of highly reliable energy storage systems. However, selecting the absolute optimal battery chemistry for a specific Electric Vehicle (EV) platform is no longer a straightforward engineering task. It has evolved into a highly complex, multi-dimensional decision-making puzzle filled with severely conflicting parameters. This thesis critically examines the revolutionary integration of Artificial Intelligence (AI) and Machine Learning algorithms into traditional Multi-Criteria Decision-Making (MCDM) frameworks. By deeply analyzing the application of methods such as TOPSIS and AHP, alongside predictive "Digital Twin" modeling, this research demonstrates how AI completely eliminates the biases of human intuition. The integration of these advanced computational tools allows automotive engineers to rapidly balance energy density, thermal safety, long-term cycle life, and manufacturing costs, ultimately accelerating the deployment of safe, highly optimized zero-emission vehicles.