Battery health state estimation method based on data feature mining

The health status estimation of lithium-ion battery is a challenging through measurement. To establish a connection between battery health status and data features, a battery State of Health (SOH) estimation method based on data feature mining is proposed. Four features are extracted from the battery charging curve, and the grey correlation analysis is used to determine the high correlation between features and health status. The method combines a Backpropagation (BP) neural network with Genetic Algorithm (GA) for feature training and learning, enabling the estimation of battery SOH. The feasibility of the proposed method is validated using the NASA battery dataset. The results show that the battery SOH estimation method proposed in this paper outperforms the traditional BP neural network method achieving accurate estimation.