Power Prediction-Based Model Predictive Control for Energy Management in Land and Air Vehicle with Turboshaft Engine

In recent years, the green aviation technology draws more attention, and more hybrid power units have been applied to the aerial vehicles. To achieve the high performance and long lifetime of components during varied working conditions, the effective regulation of the energy management is necessary for the vehicles with hybrid power unit (HPU). In this paper, power prediction-based model predictive control (P2MPC) for energy management strategy (EMS) is proposed for the vehicle equipped with HPU based on turboshaft engine in order to maintain proper battery's state of charge (SOC) and decrease turboshaft engine's exhaust gas temperature (EGT). First, a modeling approach based on data-driven method is adopted to obtain the mathematical model of turboshaft engine considering time delay and inertial of states. An integrated power predictor consisting of the classification of input status and the subpredictors are developed based on the deep learning method to improve the accuracy of the prediction model of the model predictive control (MPC). Subsequently, an EMS based on MPC using the proposed power predictor is introduced to regulate the SOC of battery and the EGT of turboshaft engine. The comparison with experimental results shows the high accuracy of mathematical model of turboshaft engine. The simulation results show the effectiveness of the proposed EMS for the vehicle, and the effects of different weight coefficients of objective function on the proposed EMS are discussed.