Model reference adaptive control with multi-rate type neural network for electro-pneumatic servo system

In this paper, we propose a design scheme which combines a model reference adaptive control with a neural network (NN) for the electropneumatic servo system. In this design scheme, we adopt a multirate type NN in which an update-time of weights is selected as multiple of a sampling-time. The effectiveness of the proposed design scheme is confirmed by experiments using the existent electropneumatic servo system.