基于MARS的电池荷电状态估计

将多元自适应回归样条估算方法应用于大容量磷酸铁锂电池组的SOC估计,将电压、电流和温度共同作为输入变量。对实验所得数据进行标准化处理,将处理后的数据进行训练,得到SOC估计的精简数学模型,并对模型进行了验证。仿真实验结果表明该方法可以提高SOC估算精度。

Battery SOC estimation based on MARS

A method of multivariate adaptive regression spline (MARS) was first applied to the estimate of the state of charge (SOC) of the large capacity of lithium iron phosphate battery.The input variables used in this method were temperature,voltage and current.Firstly,the data getting from experiment were standardized,an explicit mathematical form of SOC was obtain after modeling using training data.And then the resulting model was validated.The accuracy of the estimate of SOC was improved by using this technology with simulation.