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 control system by directly estimating an actuator-matched, un-modeled, nonlinear disturbance, in closed-loop, and compensating for it. As disturbances are generally known to be bounded, the nominal NN-control element is modified to retain the known bound of the disturbance as its maximum amplitude. The linear control element is conditioned by an anti-windup (AW) compensator which ensures performance close to the nominal controller and swift recovery from saturation