Performance oriented anti-windup for a class of neural network controlled systems

This paper presents a conditioning scheme for a linear control system which is enhanced by a neural network (NN) controller and subjected to a control signal amplitude limit. The neural network controller improves the performance of the linear ciintrol system by directly estimating an actuatormatched, un-modelled, nnn-linear disturbance, in closed-loop, and cnm ensating for it. As disturbances are generally known tu he bounled, the nominal NN-control element is modified to retain the known hound of the disturbance as its maximum amplitude. The linear control element is ronditianed hy an anti-windup (AW) compensator which ensures performance close to the nomind controller and swift recovery from saturation.