Simple Neural Network Fits the Aerodynamic Parameters of the Aircraft

During the flight of the aircraft, whether the aerodynamic parameters can be obtained accurately and in real time will directly affect its flight state. The traditional method of obtaining aerodynamic parameters has the problems of time-consuming calculation and slow response. However, the general neural network method needs to consider many factors such as the aerodynamic shape and flight altitude of the aircraft. In this paper, a simpler and more convenient network is designed by combining the advantages of the two methods, which not only has high response characteristics but also can effectively fit the coefficients of the aircraft without considering the shape of the aircraft. The simulation results show that the neural network not only has excellent fitting generalization ability, but also can be better applied to the flight experiment of the flight mission with the predicted aerodynamic parameters. Neural networks convert complex calculations into linear operations, greatly improving the speed of data prediction and making the overall response faster.