Régulateur glissant neuronal de la vitesse d’un moteur asynchrone

Abstract

The sliding mode control technique is a particular type of variable structure control. It adapts only with nonlinear systems, which shows the interest of using the technique in sliding mode to control the speed of the asynchronous machine. Its dynamics are insensitive to the parametric variations and external disturbances. In this work, the integration of neural networks with sliding mode control for asynchronous machine speed control combines the advantages of decreasement of undulation. The results of simulations (under the Matlab / Simulink software) are very satisfactory. However, the control by sliding mode requires knowledge of the mathematical model of the system with uncertainties born. To remedy this problem, the neural network technique is used to reduce the chattering phenomenon. This adaptive and intelligent approach offers an improved control performance, particularly useful in environments with dynamic uncertainties and load variations