Estimation of Aircraft Lateral-Directional Parameters Using Neural Networks

Abstract

A recently proposed method (christened ‘ ‘ the Delta method’ ’) of estimating aircraft parameters from e ight data using feed-forward neural networks is applied for the extraction of lateral ‐directional parameters from simulated as well as real-e ight data. The neural network is trained using aircraft motion and control variables as the network inputs and aerodynamic coefe cients as the network outputs; the trained network is used to predict aerodynamic coefe cients for a suitably modie ed input e le. An appropriate interpretation and manipulation of such input ‐output e les yields the estimates of the parameters. Flight data for lateral ‐directional dynamics are analyzed for various combinations and types of control inputs, and suitable control input forms are identie ed for better estimation via the proposed method. Robustness of the method with respect to measurement noise is demonstrated by its applicability to simulated e ight data with pseudomeasurement noise, and to real-e ight data.