Position control of an ER valve-cylinder system via neural network controller

A system of position control which uses a single-rod cylinder activated by an electrorheological (ER) valve is presented. Following the manufacture of a silicone oil-based ER fluid, a Bingham property of the ER fluid is first tested as a function of electric field in order to determine operational parameters for the ER valve. The ER valve with multi-channel plates is then designed and manufactured. Subsequently, pressure drops of the ER valve are evaluated with respect to the number of electrodes as well as the intensity of the electric fields. The ER valve-cylinder system is formulated and governing equations of motion for the system are derived. From the state-space model for the governing equations, a neural network control scheme is synthesized to achieve the position control of the cylinder system. Both regulating and tracking control responses are experimentally evaluated and presented in order to demonstrate the effectiveness of the proposed methodology. (C) 1997 Elsevier Science Ltd.