A comparison between two pneumatic servovalves models

Abstract

This paper presents a study where the models of two pneumatic servovalves are compared. The models are based on artificial neural networks and enable the use of air mass flow as the synthesized control action, thus rendering the overall pneumatic system affine. Control techniques requiring this condition on the system model can therefore be directly used. The impact of the servovalve characteristic curves on the neural network models is discussed and it is shown that unreachable mass flow references do not lead to a faulty behaviour when the models are used for control tasks.