Control of a loaded induction machine using a feedforward neural network
Mohamed Saber Chtourou, Nabil Derbel, Mohamed Ben Ali Kamoun · International Journal of Systems Science · 1996
Neural networks have been the subject of great interest in the control field. They seem to offer good ability to solve complex tasks. In this paper, some results of using a neural network for the nonlinear control of an induction machine's speed are presented. The neural controller is a feedforward neural network identified off-line. The backpropagation learning algorithm has been used for the off-line identification of the plant inverse neural model which provides the control action. Simulations under measurement noise and environmental condition variations have been investigated and comparison of performance has been made with an adaptive neural controller. The obtained results show the efficiency and the implementation simplicity of the presented strategy