期刊文献+

电动汽车电池荷电状态估算

Evaluating charge state of electric vehicle battery
下载PDF
导出
摘要 为了精确估计电动汽车电池的荷电状态(SOC),将模糊神经网络和最小二乘支持向量机分别用来估计电池的SOC,然后将两种方法相结合,交替地使用来预测电池SOC.在美国能源部纯电动汽车试验计划提供的混合工况UDDS-NYCC-US06_HWY驾驶循环实验中提取电池模型参数的充电/放电测试周期,用电池电流,电池电压和电池温度为独立变量,试验进行了80 Ah镍氢电池与动力测试周期来预测电池SOC.结果表明,此方法不仅可以准确的估算SOC,而且能减少计算量. To exactly evaluate the state of the charge(SOC) of the electric vehicle’s battery, the fuzzy neural network and least squares support vector machines were used separately at first and then the two methods were combined and employed alternately to predict the battery SOC. The battery model parameters of charging/discharging testing period were drawn from UDDS-NYCC-US06_HWY driving cyclic experiment, which was provided by the U.S. department of energy’s electrical vehicle. Using the data of battery current, voltage and temperature as the independent variables, test on an 80 Ah Ni-MH battery and the cycle of the battery’s power was conducted to predict the battery’s SOC. Results showed that the method not only can accurately estimate the SOC but also can reduce the amount of calculation.
出处 《武汉工程大学学报》 CAS 2015年第10期51-56,共6页 Journal of Wuhan Institute of Technology
基金 国家自然科学基金资助项目(61072121)
关键词 电动汽车 模糊神经网络 最小二乘支持向量机 电池荷电状态 electric vehicle fuzzy neural network least square support vector machine state of charge
  • 相关文献

参考文献7

二级参考文献25

共引文献173

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部