The use of neural networks in adaptive control

Abstract

An adaptive control system is a system that detects changes in the plant parameters and makes necessary adjustments to the systems performance. This thesis examines the use of parallel distributed processing systems (neural networks) in adaptive control. A general neural network structure is introduced and a description of the Backpropagation paradigm is given. A discussion of adaptive control theory including the one step ahead prediction control algorithm and the linear least squares estimation is given. A neural network structure consistent with adaptive control theory is developed and tested by simulating the lateral and directional motion of the A-4 aircraft. the network output is then compared to the output of the true system. The purpose of this thesis is to develop and test a neural network structure capable of performing the parameter estimation and control functions of an adaptive controller.