Identification and Validation of the Cessna Citation X Longitudinal Aerodynamic Coefficients in Stall Conditions using Multi-Layer Perceptrons and Recurrent Neural Networks

The increased number of accidents in general aviation due to loss aircraft control has necessitated the development accurate aerodynamic airplane models. These models should indicate linear variations coefficients steady flight and highly nonlinear stall post-stall conditions. This paper presents a detailed methodology model lift, drag, pitching moment regime, using Neural Networks (NN). A system identification technique was used develop from data. data were gathered level-D Research Aircraft Flight Simulator (RAFS) that execute maneuvers. Multilayer Perceptrons Recurrent learn find correlations between parameters. is employed here optimize neural network structures ideal hyperparameters: training algorithms activation functions developed successfully validated by comparing predicted for given pilot inputs with experimental obtained Cessna Citation X RAFS same inputs.