THE ADDITION OF NEURAL NETWORKS TO THE INNER FEEDBACK PATH IN ORDER TO IMPROVE ON THE USE OF PRE-TRAINED FEED FORWARD ESTIMATORS

A learning control architecture which uses a multi-layer feed forward neural network with error back propagation is described. The architect ure includes a feed forward estimator which is pre-trained and a feedb ack controller which continues to learn. The properties of the archite ctures are investigated through a series of experiments, and the appli cation of the prototype adaptive controllers is described. To examine the performance of this controller, square wave demand signals are app lied to the controller and the results are presented.