A multiple aging factor interactive learning framework for lithium-ion battery state-of-health estimation

Abstract

As lithium-ion batteries are widely used in electric vehicles, it has become critical to accurately estimate the state-of-health of the battery. While neural networks have been proven to be effective for state-of-health estimation, such networks primarily focus on feature modeling of raw data without exploiting inherent correlation among multiple dimensional information in the raw data, limiting the estimation accuracy. We thereby propose an interactive learning network for state-of-health estimation. The novel network simultaneously models features and learns correlations among multiple dimensional information using multiple layer perceptron in an interactive manner. We then extract multiple aging factors from the raw voltage and current data as network inputs, which enables knowledge associated to state-of-health of the battery to be encoded in the proposed network. In addition, benefiting from aging factors in lower dimensions than the raw data, computational overhead of the network are significantly reduced. Comprehensive experiments are conducted on two widely-adopted datasets. The experimental results confirm that our proposed network performs accurate state-of-health estimation within a mean absolute error of less than 3% in both of the two datasets, outperforming previous recurrent neural network and Transformer-based methods. Moreover, computational load comparison further demonstrates the potential of the proposed framework in battery management systems.