论文部分内容阅读
针对蓄电池荷电状态估计问题,将神经网络方法用于电动车蓄电池荷电状态的估计。依据蓄电池荷电状态与可测量参数之间的非线性关系,建立了基于BP神经网络与RBF神经网络的蓄电池荷电状态预测模型。仿真结果表明,经过训练后的预测模型,可以通过蓄电池的端电压、工作电流以及蓄电池的内阻参数预测蓄电池的实时荷电状态。通过比较,RBF预测模型具有较好的泛化能力且稳定性更强,能够更精确的估计出蓄电池的剩余容量。
In view of battery state of charge estimation, neural network method is used to estimate the state of charge of battery in electric vehicle. Based on the non-linear relationship between battery state of charge and measurable parameters, a battery state-of-charge prediction model based on BP neural network and RBF neural network was established. The simulation results show that the trained predictive model can predict the real-time state of charge of the battery through the terminal voltage of the battery, the operating current and the internal resistance of the battery. By comparison, the RBF prediction model has better generalization ability and stability, and can more accurately estimate the remaining capacity of the battery.