Life Prediction under Charging Process of Lithium-Ion Batteries Based on AutoML

Accurate online capacity estimation and life prediction of lithium-ion batteries (LIBs) are crucial to large-scale commercial use for electric vehicles. The data-driven method lately has drawn great attention in this field due efficient machine learning, but it remains an ongoing challenge the feature extraction related battery lifespan. Some studies focus on features only constant current (CC) charging phase, regardless joint impact including voltage (CV) phase aging, which can lead deviation. In study, we analyze CC CV phases using optimized incremental (IC) curve, showing strong relevance between IC curve as well Then, model based automated learning (AutoML) is established, automatically generate a suitable pipeline with less human intervention, overcoming problem redundant information high computational cost. proposed verified NASA’s LIBs cycle datasets, MAE increased by 52.8% RMSE 48.3% compared other methods same datasets training method, accomplishing obvious enhancement small-scale datasets.