基于深度强化学习卡尔曼滤波锂离子电池SOC估计

Estimating the State of Charge of Li-ion Batteries Based on Reinforcement Learning of Kalman Filters

针对锂离子电池的荷电状态(state of charge,SOC)估算精度,设计了一种基于深度强化学习卡尔曼滤波锂离子电池SOC估计算法.首先以锂离子电池二阶RC等效电路为研究对象,应用卡尔曼滤波算法,构建了锂离子电池的离散系统数学模型;然后结合深度强化学习思想,构造了一种深度强化学习卡尔曼滤波算法,该算法利用贝叶斯规则确保最佳协方差.仿真结果表明,深度强化学习卡尔曼滤波算法对锂离子电池荷电状态的精度有较好的估计.

In order to improve the estimation accuracy of the state of charge(SOC)of the lithium-ion battery,an algorithm to estimate the state of charge of lithium-ion batteries based on reinforcement learning of Kalman filters was proposed.Firstly,a second-order RC equivalent circuit model was introduced,and a state-space model of coefficient of variation of the lithium-ion battery was structured by using Kalman filter.Then,a reinforcement learning algorithm of Kalman filters was structured,while Bayes rule was used to ensure optimal covariance.Simulation shows that the algorithm can more accurately estimate the state of charge of the batteries.