Identification of induction machines using artificial neural networks

This paper shows an analysis of the use of artificial neural networks (ANNs) for induction machines identification, in order to use afterwards for the control of induction machines. A multilayer perceptron neural network with a hidden layer is trained with the backpropagation algorithm to identify the induction motor (IM) for getting the IM neural model. The neural network training process is analyzed with different scenarios (different number of hidden layer neurons, different learning rates and different sampling rates) in order to get neural networks parameters for practical implementations. Finally, the results of the trained neural networks for different load torque are shown