Elman neural network-based nonlinear state estimation for induction motors

This study presents a recurrent neural network (RNN)-based nonlinear state estimator that uses an Elman neural network structure (ENN) for state estimation of a squirrel-cage induction motor. The proposed algorithm only uses the measurements of the stator currents and the rotor angular speed, and it learns the dynamic behavior of the state observer from these measurements through prediction error minimization. A squirrel-cage induction motor was fed from sinusoidal, 6-step, and pulse-width modulation (PWM) supply sources at different times in order to observe the performance of the proposed estimator for different operation conditions. Estimation results showed that the proposed algorithm is capable of estimating the states of an induction motor and performs better than extended Kalman filtering (EKF) in terms of accuracy and convergence speed.