A Comparison of Charging Voltage Image Coding Methods for Lithium-Ion Battery State of Health Estimation

Accurate estimation of the state of health (SOH) of lithium-ion batteries is a key initiative to guarantee their service reliability in complex operating environments. Using one-dimensional time series data to transform two-dimensional image for battery degradation feature extraction can improve the accuracy of battery SOH evaluation, reduce the complexity of evaluation model and the demand for the amount of test data. Although existing studies have attempted to apply image coding techniques to enhance the degradation features of original data, the advantages and disadvantages of different image coding methods have not been systematically compared. Therefore, in this work, five commonly used image coding methods including recurrence plots, Gramian angular summation field, Gramian angular difference field, relative position matrix, and time series data folding are selected and comprehensively compared. Firstly, the original one-dimensional voltage signal is encoded into a two-dimensional image, which is then inputted into the CNN-GRU-based SOH prediction model, and finally the future battery SOH value is output. The experimental results show that there are differences in the applicable stages and conditions of different coding methods, so they need to be adapted with specific application scenarios, which is the next research direction.