NARMAX method for estimating the residual capacity of Ni/MH battery pack for electric vehicle
电动车用Ni/MH电池组剩余容量的非线性自回归滑动平均预测

An accurate state of charge(SOC) determines the residual diving distance of electric vehicles. For evaluating the state of charge(SOC) of the Ni/MH battery pack for electric vehicle, we propose an identification approach using NARMAX(nonlinear auto-regressive moving average with exogenous inputs) model. Employing the federal urban driving schedule(FUDS) tested data and adopting the simplified linear approximation of NARMAX method, we build the multiinput model for the SOC of the battery pack. This model is used for predicting the real-time SOC, and the results are compared with the tested data. The comparison of the predicted results with the tested data shows that the proposed method is simple and efficient. The maximum relative error of the estimation results is within 1%.