The battery aging of lithium-ion batteries is a fundamental factor in maintaining the performance, safety, and reliability of electric vehicles (EVs). Accurate estimation of battery aging is vital for optimizing battery usage, predicting maintenance needs, and ensuring the longevity of EV batteries. This paper introduces a novel methodology that integrates artificial intelligence (AI) techniques to enhance battery aging determination. While these methods provide foundational insights, they often lack precision due to variability in operating conditions and individual battery behaviors. To address these limitations, we propose a hybrid approach that combines AI-driven data analysis. Specifically, we utilize Feedforward Neural Networks (FNN), Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM) networks to improve battery aging estimation accuracy by predicting the capacity of battery, which could be used to predict state of health (SOH), remaining useful life (RUL) and end of life (EoL). AI integration allows for adaptive learning, giving a high prediction based on real-time data and historical process.