Stable Neuro-Flight-Controller Using Fully Tuned Radial Basis Function Neural Networks

TLDR

The authors develop a flight control scheme that integrates a radial basis function network to assist a conventional controller. The scheme employs an online‑learning RBFN with variable Gaussian functions and a Lyapunov‑based tuning rule that updates centers, widths, and output weights, extending Gomi and Kawato’s adaptive strategy. The tuning rule guarantees system convergence, markedly improves tracking accuracy, and simulation on an F8 aircraft demonstrates superior performance, with potential for dynamic neuron addition/pruning to yield a more compact network. Reference: Gomi & Kawato, Neural Networks, 1993.

Abstract

A e ight control scheme in which a radial basis function network (RBFN)aids a conventional controller has been developed. The RBFN controller, consisting of variable Gaussian functions, uses only online learning to represent the local inverse dynamics of the aircraft system. With a Lyapunov synthesis approach, a tuning rule for updating all of the parameters of the RBFN (including centers, widths, as well as the weights of the output layer ) is derived, which extends Gomi and Kawato’ s strategy, where only the weights were adaptable. (Gomi, H., and Kawato, M., “ Neural Network Control for a Closed-Loop System Using Feedback-Error Learning,” Neural Networks , Vol. 6, No. 7, 1993, pp. 933 ‐946). The proposed tuning rule guarantees the convergence of the overall system and greatly improves the tracking accuracy. Simulation studies using an F8 aircraft longitudinal model illustrate the superior performance of the proposed scheme. The simulation studies further indicate that the results can be extended to a dynamic RBFN in which the hidden neurons can be added /pruned, thus producing a more compact network structure.