Research on Energy Management Strategy of Diesel Hybrid Electric Vehicle Based on Decision Tree CART Algorithm

Abstract

Abstract Aiming at the emission of nitrogen oxides from hybrid electric vehicles (HEV), a strategy of diesel hybrid energy management based on decision tree CART algorithm was proposed.Firstly, a classification algorithm combining decision tree and regression tree is proposed to predict the trend change relationship of a case from one or more predictive variables according to the category and variable characteristics.Secondly, by controlling the torque distribution between the engine and the motor, an additional degree of freedom is introduced to adjust the trade-off between pure fuel economy and pure restriction.Finally, the simulation method is used to understand the system performance and adjust the proposed energy management strategy.The results show that in the proposed energy management strategy for diesel hybrid power, the reduction of NOx has an impact on fuel consumption, and the potential of NOx emission can be limited by choosing the best operating point and limiting engine power.