Neural-network-based variable structure control of electrohydraulic servosystems subject to huge uncertainties without persistent excitation

A novel scheme investigating a radial-basis-function neural network (RBFNN) with variable structure control (VSC) for electrohydraulic servosystems su bject to huge uncertainties is presented. Although the VSC possesses some a dvantages (e.g., fast response, less sensitive to uncertainties, and easy i mplementation), the chattering control input often occurs, The reason for a chattering control input is that the switching control in the VSC is used to cope with the uncertainties. The larger the uncertainties which arise, t he larger switching control occurs. In this paper, an RBFNN is employed to model the uncertainties caused by parameter variations, friction, external load, and controller, A new weight updating law using a revision of c-modif ication by a time-varying dead zone can achieve an exponential stability wi thout the assumption of persistent excitation for the uncertainties or radi al basis function. Then, an RBFNN-based VSC is constructed such that some p art of uncertainties are tackled, that the tracking performance is improved , and that the level of chattering control input is attenuated, Finally, th e stability of the overall system is verified by the Lyapunov stability cri terion.