Application of a neuro-fuzzy controller to an electrohydraulic axis

The conventional controllers are powerful tool that can be used to control systems whose behaviour is linear. Hydraulic installation behaves as strongly non-linear systems, both static and dynamic non-linearities are characterising their behaviour, during the steady-state, stationary and transient periods. Therefore, a very suitable way to control the processes whose mathematical models are very complex and present many uncertainties in parameter and structure is the use of advanced control techniques, such as Fuzzy, Neuro-Fuzzy or Neural-Networks technologies. The goal of this paper is to present results of a Neuro-Fuzzy controller for an electro-hydraulic axis achieved to control a cartesian robot with three axes. The papers present the proposed Neuro-Fuzzy implemented in MATLAB/SIMULINK and the achieved results of simulation for position control. Own subroutines for are also available in C++ Borland [6].