Rule-Based Online Energy Management Strategy for Power-Split Plug-In Hybrid Electric Vehicles

In this paper, a fixed size least square - supported vector machine (LS-SVM) algorithm is proposed to estimate the state of health (SOH) of the lithium-ion battery. First, the battery constant current discharging voltage profiles are analyzed and partial discharge curve that can be employed to describe the attenuation of the battery's SOH are extracted, and the suitable voltage range is analyzed. The discharging time is regarded as the input variable of the model. Then the fixed size LS-SVM algorithm is employed, and the corresponding support vector is selected according to Renyi entropy. The model parameters are optimized based on Bayes framework. Experimental results validate that the new method proposed in this paper can effectively track the aging of batteries. Compared with the traditional supported vector machine (SVM), the fixed size LS- SVM requires only 10 support vectors to achieve the desirable SOH estimation.