2 NEW TECHNIQUES FOR AIRCRAFT PARAMETER-ESTIMATION USING NEURAL NETWORKS

Two new techniques for estimating aircraft stability and control deriv atives (parameters) from flight data using feed forward neural network s are proposed. Both techniques use motion variables and control input s as the input file, while aerodynamic coefficients are presented as t he output file for training a neural network. For the purpose of param eter estimation, the trained neural network is presented with a suitab ly modified input file, and the corresponding predicted output file of aerodynamic coefficients is obtained. Suitable interpretation and man ipulation of such input-output files yields the estimated values of th e parameters. The methods are validated first on the simulated flight data and then on real flight data obtained by digitising analogue data from a published report. Results are presented to show how the accura cy of the estimates is affected by the topology of the network, the nu mber of iterations and the intensity of the measurement noise in simul ated flight data. One of the significant features of the proposed meth ods is that they do not require guessing of a reasonable set of starti ng values of the parameters as a popular parameter estimator like the maximum likelihood method does.