Variable structure control of electrohydraulic servo systems using fuzzy CMAC neural network

This paper presents a novel variable structure control (VSC) scheme based on the use of fuzzy cerebellar model articulation controller (FCMAC) for the control of electrohydraulic position servo systems. FCMAC is used to develop an adaptive equivalent control law by learning the uncertainties resulting from unmodelled dynamics and external disturbances. This feature makes it possible to use a small gain of the discontinuous control while satisfying the existence condition of the sliding mode in the presence of large uncertainties. As a result, the chattering is suppressed greatly, while the merits of the traditional VSC are maintained. The actual switching function is used to update the FCMAC weights and the existence of the sliding mode is proved. The simulations and experiments on a typical electrohydraulic position servo system are conducted to verify the effectiveness and robustness of the control scheme.