A Novel State of Charge Approach of Lithium Ion Battery Using Least Squares Support Vector Machine

Jiabo Li,Wei Meng,Shengjie Jiao,Min Ye,Xinxin Xu

doi:10.1109/access.2020.3033451

Jiabo Li, Wei Meng + Show 3 more

Open Access

https://doi.org/10.1109/access.2020.3033451

Copy DOI

Journal: IEEE Access	Publication Date: Jan 1, 2020
Citations: 56	License type: CC BY 4.0

Affiliation: Chang'an University

Abstract

Lithium-ion batteries(LIBs) have been used in electric vehicles(EVs) because of its high energy density and no pollution. As one of the important parameters of battery management system(BMS), accurately estimating the state-of-charge (SOC) can ensure the energy distribution and safe use of the battery. Therefore, in order to obtain accurate SOC estimation, this paper improves the estimation accuracy of SOC from four aspects. Firstly, to overcome the dependence of the model on the internal parameters of the battery, this paper uses the least squares support vector machine (LSSVM) to establish the battery model. The current, voltage, temperature are used as input vectors to estimate the SOC. Besides, the parameters of LSSVM are determined by a grey wolf optimizer(GWO). The GWO can improve the ability of LSSVM model by finding the global optimal solution. Thirdly, in order to improve the estimation accuracy of SOC, a novel LSSVM model based on the sliding window is proposed. The SOC estimated at the previous time, together with voltage, current and temperature measured at the current time are selected as the input vectors by sliding window method to improve the SOC accuracy. Finally, the effectiveness of the proposed model is verified under different driving conditions at different temperatures by comparing with other estimators. The comparison results indicate that the SOC estimation error(MAE) can be controlled within 1%, the root mean square error (RMSE) decreases from 0.89% to 0.22%, which are verified the effectiveness and robustness of the model.

Highlights

With the large-scale popularization of new energy electric vehicles (EVs), lithium-ion batteries (LIBs) have a longer cycle life, no memory effect in the process of charging and discharging, and no pollution to the environment in the process of production and recycling [1,2,3,4] are widely used
The core contributions are as follows: (1) the calculation ability of least squares support vector machine (LSSVM) model does not depend on the internal parameters of battery, three basic battery parameters are selected as inputs to estimate SOC; (2) Grey wolf optimizer (GWO) is used to identify model parameters, and the effectiveness of GWO is verified by cross-validation(CV) method; (3) the sliding window method is proposed to update the number of input vectors of LSSVM to improve the estimation accuracy of SOC; (4) the robustness of the proposed model are verified under federal urban driving schedule (FUDS) and dynamic stress test (DST) conditions at different temperatures
The results show that the estimation error of SOC decreases with the increase of temperature, and the LSSVM model based on GWO optimization has high accuracy

Summary

INTRODUCTION

With the large-scale popularization of new energy electric vehicles (EVs), lithium-ion batteries (LIBs) have a longer cycle life, no memory effect in the process of charging and discharging, and no pollution to the environment in the process of production and recycling [1,2,3,4] are widely used. Deng Z et al [23] proposed Gaussian process regression (GPR) to apply to SOC estimation of LIBs, which can obtain better accuracy, and the confidence interval is within 3.9%.The SVM [24,25] was proposed as a new method based on statistical learning theory It improves the learning ability and generalization ability of the machine by seeking the minimum structural risk. The core contributions are as follows: (1) the calculation ability of LSSVM model does not depend on the internal parameters of battery, three basic battery parameters are selected as inputs to estimate SOC; (2) Grey wolf optimizer (GWO) is used to identify model parameters, and the effectiveness of GWO is verified by cross-validation(CV) method; (3) the sliding window method is proposed to update the number of input vectors of LSSVM to improve the estimation accuracy of SOC; (4) the robustness of the proposed model are verified under FUDS and DST conditions at different temperatures.

The theory of LSSVM

SOC Estimation Based on the sliding window method

Results and Discussions

Conclusion