Dj. Linse et Rf. Stengel, IDENTIFICATION OF AERODYNAMIC COEFFICIENTS USING COMPUTATIONAL NEURALNETWORKS, Journal of guidance, control, and dynamics, 16(6), 1993, pp. 1018-1025
Precise, smooth aerodynamic models are required for implementing adapt
ive, nonlinear control strategies. Accurate representations of aerodyn
amic coefficients can be generated for the complete flight envelope by
combining computational neural network models with an estimation-befo
re-modeling paradigm for on-line training information. A novel method
of incorporating first partial derivative information is employed to e
stimate the weights in individual feedforward neural networks for each
aerodynamic coefficient. The method is demonstrated by generating a m
odel of the normal force coefficient of a twin-jet transport aircraft
from simulated flight data, and promising results are obtained.