A prediction model for remaiming capacity in batteries based on least square support vector machine

A novel prediction model for remaining capacity of batteries based on least square support vector machine(LS-SVM) was proposed. With battery ending voltage and degree of new as inputs,remaining capacity of resting batteries as output,test was taken to get data samples.Throghout data samples above,LS-SVM model was established,and remaining capacity of batteries can predict by the model. Experimental results show that the construction speed of this LS-SVM model is higher than that of the SVM model,while the prediction errors are less. Moreover,compared with BP model,the accuracy and speed of prediction are much higher than that of the former.