A BP neural network-Ant Lion Optimizer and UKF method for SOC estimation of lithium-ion batteries

Abstract

Accurate state of charge (SOC) estimation is of great significance to promote the development of new energy vehicles. And a battery model’s accuracy is of great significance for the battery SOC estimation accuracy. To this end, a method based on back propagation neural network-Ant Lion Optimizer (BPNN-ALO) and unscented Kalman filter (UKF) is proposed. First, a 2-RC battery model is established and BPNN is used to fit the OCV-SOC corresponding relationship. Second, the BPNN and ALO are combined to complete the battery model’s parameter identification, and UKF is used to complete SOC estimation. Finally, verify the BPNN-ALO-UKF under two working conditions, and compare it with the other two methods. The test results show that the proposed method has higher SOC estimation accuracy, the minimum values of Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) are only 0.51% and 0.40%, respectively. And under different working conditions, it also has a better generalization and robustness.

Improved BP neural network algorithm to SOC estimation of mine power supply

“…At present, as primary and secondary storage batteries for mine power supply, The charging state of the battery -The main estimation methods of SOC are the ampere-hour method, the internal resistance method, the Kalman filter method, the linear model method, the neural network algorithm, etc. [1][2][3][4][5][6] . Currently, the mine's standby power supply utilizes an amperometric time method with pre-and post-corrections, but its overall accuracy and reliability are inadequate [7][8][9][10] .…”

Optimal Information Fusion-Based Strong Tracking Filter for State of Charge Estimation of Lithium-Ion Batteries

“…Once the model is determined and the parameters are identified, SOC estimation can be estimated by nonlinear system control methods and filtering techniques. 14,15 The Kalman filters, including the extended Kalman filter (EKF), [16][17][18] unscented Kalman filter (UKF), [19][20][21] and cubature Kalman filter (CKF), 22 have become one of the most effective estimators due to their excellent estimation performance in non-linear systems. The particle filter (PF) [23][24][25][26] and H-infinity filter (HIF) [27][28][29] have higher robustness and estimation accuracy compared to the Kalman filters because they have no strict limitations on noise types.…”