EXPERIMENTAL DETERMINATION OF ELECTRICAL AND MECHANICAL PARAMETERS OF DC MOTOR USING GENETIC ELMAN NEURAL NETWORK

The most suitable and generalized neural network that represents the controlsystem dynamics is the Elman Neural Network (ENN). This is due to its ability tomemorize and emulate the system states. Moreover, ENNs learned by Geneticalgorithms are found to be more representative to system order in terms of itsstructural complexity in comparison to those learned by back propagationalgorithm. This facility is utilized efficiently to find the minimum ENN structurethat represents the discrete-time state space model of the DC motor. Then bycomparing the ENN weights with the well-known discrete-time state spaceequation in terms of the motor physical parameters (moment of inertia, torqueconstant, armature inductance, etc.), these parameters can be obtained.