摘要
针对电动汽车动力电池非线性强、普通神经网络模型预测电池组的剩余荷电状态(SOC)时面临收敛速度慢、精度低的问题,本文提出利用粒子群优化神经网络(PSOBP)估算动力电池SOC。该方法以单体电池电压、电流作为神经网络模型的输入,电池SOC作为输出,采用粒子群优化BP神经网络的权值和阈值,解决普通神经网络容易陷入局部极小值的问题。仿真结果表明,该方法估算电池SOC具有较高的预测精度,收敛速度快。
Aiming at the problems of strong non-linearity of electric vehicle power batteries and the common neural network model in predicting the remaining state of charge(SOC)of the battery pack,the convergence rate is slow and the accuracy is low,particle swarm optimization neural network(PSO-BP)is proposed to estimate SOC of power battery in the paper,This method takes the voltage and current of the single cell as the input of the neural network model and the battery SOC as the output,and uses particle swarm optimization to optimize the weight and threshold of the BP neural network.The simulation results show that the method has higher prediction accuracy,faster convergence speed.
作者
王晨
王琪
张萌
Wang Chen;Wang Qi;Zhang Meng(College of Electrionic Information Engineer Xi'an Technological University,Xi'an 710021,China)
出处
《单片机与嵌入式系统应用》
2020年第6期20-23,29,共5页
Microcontrollers & Embedded Systems
基金
陕西省科技重点研发计划一般项目(2019GY084)。
