Nonlinear Aerodynamic Modeling of Hansa-3 Aircraft Using Neural-Gauss-Newton Method

Abstract

The paper presents the nonlinear longitudinal aerodynamic modeling using Neural-GaussNewton (NGN) method from real flight data of Hansa-3 aircraft. The NGN method is an algorithm that utilizes Feed Forward Neural Network and Gauss-Newton optimization to estimate the parameters and it does not require a priori postulation of mathematical model or solution of equations of motion. The Kirchhoff’s quasi-steady stall model was used to include the nonlinearity in the aerodynamic model used for parameter estimation. Before application to the flight data at high angles of attack, the method was validated on flight data at moderate angles of attack. The results obtained in terms of stall characteristics and aerodynamic parameters were encouraging and reasonably accurate to establish NGN as a method for modeling nonlinear aerodynamics using flight data at high angles of attack. The supremacy of NGN was established by comparing the NGN estimates to that of Maximum Likelihood.