Comparative Analysis of RUL and SOH Prediction Algorithms using Machine Learning Techniques

This study explores data-driven methodologies for State of Health (SOH) and Remaining Useful Life (RUL) prediction of lithium-ion batteries, vital for electric vehicle (EV) adoption. Leveraging NASA and Oxford Battery Degradation datasets, advanced state of the art machine learning techniques like LSTM networks and Transformers and Gated Recurrent Unit (GRU) are integrated to develop and validate a predictive model. Challenges such as non-linear behavior and limited data are addressed with a novel neural network. A comprehensive literature review along with comparative analysis is done to assess the better performing model and it’s strengths compared to others. The study advances battery health prediction technologies, enhancing EV battery reliability and efficiency.