Energy management optimization controls of electric-diesel hybrid trains based on MPC-PMP
A suitable energy management strategy can improve the efficiency of train hybrid systems and reduce fuel consumption costs.In response to the issue of the Pontryagin's Minimum Principle(PMP)strategy requiring prediction of whole operating conditions,we proposed an energy management strategy based on Model Predictive Control(MPC)with the goal of minimizing fuel consumption,which can be applied online.Firstly,a speed prediction model was established based on Long Short Term Memory(LSTM)neural network;Then,based on the PMP algorithm,rolling optimization was carried out in the time domain of speed prediction,and the optimal power control sequence is solved at each moment;Finally,according to actual operating conditions,the energy management results of the MPC-PMP strategy,offline PMP strategy,and traditional threshold method were compared.The simulation results show that although the fuel consumption rate of MPC-PMP strategy is slightly lower than that of the offline PMP strategy,lower by 14.34%than that of the traditional threshold method strategy,and the MPC-PMP strategy meets real-time requirements.
energy management strategyhybrid systemPontryagin's Minimum Principlemodel predictive controllong short term memory neural network
NETL
NSTL
万方数据
