In this paper, a neural network approaches for the identification of a separately excited DC motor (SEDCM) loaded with a centrifugal pump load is applied. The NARX (Nonlinear Autoregressive Network with eXogenous Inputs) Network using to obtain a good quality model to explain the input – output behaviour of a DC motor drive system. The motor is assumed a black box. The load and the motor parameters are assumed unknown. The NARX recurrent neural networks have the potential to capture the dynamics of nonlinear dynamic system by presenting a suitable set of input/output patterns generated by the dynamic system. The backpropagation algorithm was used in order to improve performance accuracy to the NARX model.
DC motors, Identification, Neural Networks, NARX Model