基于BP神经网络的蓄电池充电控制优化研究

为了对蓄电池的充放电控制过程进行优化,根据其物理模型和化学反应机理,在Simulink环境中搭建铅酸蓄电池的三阶动态仿真模型.设置不同的实验测试条件,分析不同条件对蓄电池端电压和荷电状态(SOC)的影响.依据马斯最佳充电理论,基于BP神经网络算法控制蓄电池的充电电流,并与分阶段变流充电方式进行对比.实验和仿真测试结果表明,所建模型的准确率高,新型充电控制策略能更好地逼近马斯充电曲线,达到提高充电效率和延长蓄电池使用寿命的目的.

Research on Battery Charging Control Optimization Based on BP Neural Network

In order to optimize the charge and discharge control process of the battery,a third-order dynamic simulation model of lead-acid battery is built in the Simulink environment according to its physical model and chemical reaction mechanism.The different experimental conditions are set,then the influence of different conditions on the voltage and state of charge (SOC) of the battery is analyzed.According to the best charging theory of Masi,the charging current of the battery is controlled based on the BP neural network algorithm,and compared with the staged charging method.The experimental and simulation results show that the proposed model has high accuracy,and the new charging control strategy can better approach the charging curve of Masi,so as to improve the charging efficiency and prolong the battery life.