A novel RBFNN-UKF-based SOC estimator for automatic underwater vehicles considering a temperature compensation strategy

Accurate state of charge (SOC) estimation of batteries is a prerequisite for the reliable operation of automatic underwater vehicles. Currently, the accuracy of traditional SOC evaluation algorithms deteriorates significantly at low temperatures and low SOCs. Hence, a novel SOC estimator is proposed in this study, consisting of three efforts. Firstly, a new radial basis function neural network (RBFNN) battery model is built to replace the equivalent circuit model (ECM) for SOC estimation. Then, based on the relation between SOC and terminal voltage at a different temperature, a temperature compensation strategy is developed, which is an effortless operation and does not increase the computational burden. Finally, incorporating the new battery model, the temperature compensation strategy, and the unscented Kalman filter (UKF), a novel SOC estimation frame expressed as RBFNN-UKF is designed. The performance of the proposed method, including accuracy, generalization ability, and low-temperature adaptation, is evaluated systematically based on a publicly available dataset, where the inaccurate initial value and the current errors are added in each case. The results show that: (1) The SOC estimation curve of RBFNN-UKF can converge quickly to the reference curve and maintain good consistency even at low SOCs; (2) The proposed method exhibits excellent generalization capability for different dynamic cycles; (3) At low temperatures, the SOC estimation error of the RBFNN-UKF is reduced to 17 % of traditional ECM-UKF algorithm with the recursive least squares parameter identification method. The above results indicate that the proposed RBFNN-UKF-based SOC estimator has a high application value for AUVs and other vehicles working in complex environments.