Researchers have proposed a Fourier graph neural network for estimating the state of health of lithium-ion batteries while simultaneously considering spatial and temporal feature relationships. The model, called FourierGNN, is designed to improve online battery health estimation by capturing both inter-series dynamics and intra-series dependencies in battery degradation data.

Researchers have proposed an efficient feature search approach for estimating the state of health of lithium-ion batteries, aiming to reduce the reliance on manually selected aging features. The method uses Bayesian optimization to search multidimensional feature spaces and then applies an ensemble regression model to improve the accuracy and robustness of battery health estimation.