Neuro-based adaptive controller for longitudinal flight control

This paper provides some detailed analysis of the stability of the proposed direct adaptive controller for a special type of nonlinear system based on the previously published papers. The special learning algorithm similar to back propagation provides better stability and wide domain of attraction for the controller provided that the neural network parameters are chosen carefully. The controller acts as a direct adaptive controller and the weight and bias matrices are updated online without any prior offline training. It is easy to implement in real time due to less complexity in terms of absence of several neural networks. In this paper, we will be analyzing the Lyapunov stability of the neuro-based adaptive controller and show the simulation result on a F-8 aircraft control system model.