Motor rotor resistance identification based on Elman neural network

Abstract

Motor parameter identification is problem must be faced by high performance variable frequency speed adjustment system include Vector Control. Explore new effective parameter identification method possess vast theoretical and practical meanings. Motor's mathematical model has the character of high order, nonlinear and complicate coupling, the parameter change with the work state is difficult to describe with a definite function. Rotor resistance is identified with Elman neural network which has the ability of function approximation and unique feedback. The simulation result is validated by the parameter obtained with other methods and shows some advantages. It has some reference meaning to more extend motor parameter identification.

System Identification of Thermal Process using Elman Neural Networks with No Prior Knowledge of System Dynamics

“…Recurrent neural networks (RNN) have been utilized in system identification for both linear and nonlinear dynamical systems [17,18]. A particular type of RNN is the Elman recurrent neural networks(ERNN) has been considered in system identification of highly nonlinear dynamical systems, like Twin rotor system [5] and motor rotor resistance [19]. Identification and control of time-delay systems using wavelet neural networks have been achieved in [20].…”