State of charge estimation of lithium-ion battery based on improved adaptive boosting algorithm

Abstract

State of charge (SOC) is a crucial battery state to calibrate the remaining charge of lithium-ion batteries in electric vehicles. Accurate battery SOC estimation is one of the keys and difficult issues for lithium-ion batteries. To achieve SOC estimation accurately, an improved adaptive boosting algorithm called AdaBoost.RT algorithm, which is a regression ensemble algorithm and uses the extreme learning machine (ELM) as weak learners, is applied to estimate the SOC of lithium-ion batteries in this paper. And a two-step method is also proposed to denoise experimental data, which are used as the input data of the proposed SOC estimation method, to further enhance the accuracy of SOC estimation. Firstly, a complementary ensemble empirical mode decomposition with adaptive noise method (CEEMDAN) is utilized to decompose the experimental data including battery voltage and current according to the frequency of the signals to form different frequency components. Secondly, a wavelet threshold denoising method (WTD) is combined to denoise these components. The denoised components trend to form a new battery signal by the linear superposition principle and input into the proposed SOC method in this paper. The combined SOC estimation method can be called CEEMDAN-WTD-AdaBoost-ELM (CWAELM) method. To verify the proposed method, experiments are conducted under Beijing dynamic stress test (BJDST), dynamic stress test (DST), federal urban driving schedule (FUDS), and highway driving schedule (US06) conditions at 0 °C, 25 °C and 45 °C temperatures, respectively. The results show that the proposed model has good robustness and accuracy in the SOC estimation of lithium-ion batteries under various working conditions at different temperatures.