Nonlinear neural-network modeling of an induction machine

This paper presents a new approach to identify the nonlinear model of an in duction machine. The free acceleration test is performed on a 5-HP inductio n machine, and the resulting stator voltages, stator currents and rotor ang ular velocity are measured. Using the maximum likelihood (ML) algorithm, th e parameter sets of the nonlinear model at various operating conditions are estimated, Then the nonlinear model parameters are represented by the feed forward neural networks (FNN's), For validation, the simulated responses of the identified model using the measured and the simulated input patterns f or the FNN models are performed, The identified model can be utilized for p ower system transient stability analysis and for on-line computer controlle d electric drives.