Research on compact propulsion system dynamic model based on deep neural network

The on-board dynamic model is the basis of numerous advanced control technologies for modern aero-engine, and its accuracy and real-time performance are two crucial indicators. Since the simulation accuracy declines with the deviation from the ground point of the conventional compact propulsion system dynamic model (CPSDM), an improved CPSDM (ICPSDM) based on deep neural network is proposed in this paper. First, the K-means algorithm is utilized to get the sampling point, and the engine simulation data is collected in the cluster centers. Then, the batch normalize deep neural network (BN-DNN) is applied to build the ICPSDM, which can shorten the training time tremendously. The simulation results show that, in the same simulation environment, the accuracy of turbine inlet temperature T- 4 , fan surge margin SMc, thrust F, and specific fuel consumption SFC calculated by ICPSDM are 11.04, 3.17, 1.89, and 1.98 times of CPSDM, respectively, at off-design point, and the real-time performance of ICPSDM is more than 30 times faster than the component-level model.