A HYBRID-TYPE ACTIVE VIBRATION ISOLATION SYSTEM USING NEURAL NETWORKS

Vibration isolation of mechanical systems is achieved through either p assive or active vibration control systems. Although a passive vibrati on isolation system offers simple and reliable means to protect mechan ical systems from a vibration environment, it has inherent performance limitations, that is, its controllable frequency range is limited and the shape of its transmissibility does not change. Recently, in some applications, such as active suspensions or precise vibration systems, active vibration isolation systems have been employed to overcome the limitations of the passive systems. In this paper, a hybrid-type acti ve vibration isolation system that uses electromagnetic and pneumatic force is developed, and a new control algorithm adopting neural networ ks is proposed. The characteristics of the hybrid system proposed in t he paper were investigated via computer simulation and experiments. It was shown that the transmissibility of the vibration isolation system could be kept below 0.63 over the entire frequency range, including t he resonance frequency. (C) 1996 Academic Press Limited