Considering the temperature influence state‐of‐charge estimation for lithium‐ion batteries based on a back propagation neural network and improved unscented Kalman filtering. (25th July 2022)

• Record Type: Journal Article
• Authors: Lian, Gaoqi; Ye, Min; Wang, Qiao; Wei, Meng; Xu, Xinxin
• Is Part Of: International journal of energy research. Volume 46:Number 13(2022)
• Page Start: 18192
• Page End: 18211
• Publication Date: 2022-07-25
• Subjects: backpropagation neural network -- diagonalization of matrix unscented Kalman filtering -- lithium‐ion battery -- state‐of‐charge -- temperature influence; Power resources -- Periodicals; Power (Mechanics) -- Periodicals; Power resources -- Research -- Periodicals; 621.042
• DOI: 10.1002/er.8436
• Languages: English
• ISSNs: 0363-907X

Abstract

Summary: Obtaining an accurate mapping relationship between the state‐of‐charge (SOC) and open‐circuit voltage (OCV) of lithium‐ion batteries at different ambient temperatures is of great significance for realizing accurate lithium‐ion battery SOC estimation considering the ambient temperature influence. However, the desired OCV‐SOC relationship is highly nonlinear, and the conventional polynomial fitting method is likely to result in relatively large fitting errors. To solve this problem, a method based on a backpropagation neural network (BPNN) to improve the OCV‐SOC fitting accuracy is proposed, and the SOC estimation of lithium‐ion batteries considering ambient temperature influence is completed. First, the relationship between the SOC and OCV of a lithium‐ion battery at different ambient temperatures is obtained by establishing a BPNN fitting model. Second, by optimizing the covariance decomposition process, a diagonalization of matrix unscented Kalman filtering (UKF) is proposed, which improves the accuracy and stability of the filtering algorithm. Then, the forgetting factor recursive least squares algorithm is combined to accomplish the online update of battery model parameters. Finally, under three working conditions, the effectiveness and robustness of the proposed method are verified. The simulation results show that the proposed method can obtain the most accurate SOC estimation results at each temperature, and the root mean square error (RMSE) and mean absolute error (MAE) under all three working conditions are less than 1.1%. Even if there is a certain error in the initial SOC, the proposed method can ensure that the RMSE and MAE of the SOC estimation results at each temperature do not exceed 1.5%. Abstract : First, an open‐circuit voltage‐state‐of‐charge OCV‐SOC fitting method of back propagation neural network (BPNN) for lithium‐ion batteries at different temperatures is proposed, and compared with the traditional OCV‐SOC three‐dimensional polynomial fitting method at four different temperatures. The comparison results show that the proposed fitting method can obtain more accurate OCV‐SOC correspondences of lithium‐ion batteries at different temperatures. Second, the UKF commonly used in lithium‐ion battery SOC estimation is improved. Using matrix diagonalization to replace the Cholesky decomposition of the covariance matrix in the recursive process. This method can retain the original eigenspace information of the covariance matrix, transfer the covariance more accurately, and effectively enhance the stability of the filter. Finally, based on the proposed BPNN fitting model of OCV‐SOC considering temperature, combined with forgetting factor recursive least squares and the improved diagonalization of matrix UKF algorithm, the online estimation of lithium‐ion battery SOC is completed at four different ambient temperatures under three working conditions, respectively. The simulation results show that the proposed method can ensure good SOC estimation accuracy at different temperatures under various working conditions.