Procedure to Choose Alternative ANN in the Control of Electrical Drive

Intention of this paper is to introduce the way how new types of artificial neural networks can be chosen in the control of electrical drives. The procedure is demonstrated through the use of rotor time constant adaptation method in the control of electrical drive. The procedure used to choose consists of determination of the problem, selection of proper artificial neural network, choosing of the new neural networks and finally new neural networks verification. The estimation of the rotor time constant for adaptive model of MRAS is created by the help of PI-controller and then is replaced by the radial basis function network. The estimated rotor time constant is then used in the vector control of electrical drive. The different architectures of RBF network in the field of adaptation of rotor time constant parameter is discussed here. Simulations have been performed in the Matlab-Simulink.