Direct torque control of induction motor by use of neural network

General mapping regressor neural network is an incremental self organizing neural network with chains among neurons. This paper deals with the application of the general mapping regressor neural network to the direct torque control of an induction motor. In particular a classical direct torque control strategy has been learnt by the general mapping regressor neural network and then the performance of the neural controller has been verified both in numerical simulations and experimentally by means of a properly devised test bench. The good working of the general mapping regressor neural network has been experimentally verified.