Machine learning enables rapid state of health estimation of each cell within battery pack

The health and safety of the battery pack are directly influenced by the state of health of its cells. However, due to the aging inconsistency among cells and the limited measurability of physical quantities for cells within the battery pack, traditional approaches to state of health estimation of cell have significant limitations. This study introduces a machine learning approach for evaluating the state of health of cells within the battery pack. Firstly, a branch charging capacity estimator utilizing BiGRU is formulated, facilitating precise estimation of battery pack branch charging capacity across diverse charging conditions. Then, three categories of features, including aging features, inconsistency features, and operating condition features, are extracted based on aging experimental data at the battery pack level and battery pack branch charging capacity. These features are input into the support vector regression-based generic model, facilitating precise state of health estimation for all cells within the battery pack. The generalization of the model is validated under both five-stage constant current charging conditions and two-stage constant current charging conditions. Additionally, the discussion includes how the choice of model parameters affects the precision of cell state of health estimation. The method proposed enables precise monitoring of cell state of health within the battery pack, offering valuable potential for ensuring overall battery pack safety and issuing safety alerts for cells.