A prediction framework for the state of health of an electric vehicle battery pack

Because electric vehicles (EVs) are a clean energy source, understanding battery aging and health is a hot research topic. Such evaluations are essential for timely maintenance, ensuring operational efficiency, and enabling second-life applications of lithium-ion battery (LIB) packs. This study presents a new framework for predicting capacity loss in EV-compatible LIB packs using a quantum long short-term memory (QLSTM) neural network with a shared linear embedding layer, transfer learning, and a sliding window technique. The method is tested with five LIB pack datasets collected over 29 months from charging devices. Results show the approach's robustness, providing improved accuracy and efficiency, especially when trained on multiple battery datasets. Models that combine QLSTM with linear embedding layers can predict capacity with a root-mean-square error (RMSE) of less than 0.003 for the target LIB packs. These findings highlight the framework's potential to improve predictions of capacity degradation and to support sustainable energy management in EV batteries.