Induction motor flux estimation based on Artificial Neural Network left-inversion
Hao Zhang, Xianzhong Dai · 2008
This paper presents a new rotor flux estimation algorithm using neural network for induction motor, based on the left-inversion method. Using the standard fifth-order model of the three-phase induction motor in a stationary two axes reference frame, the flux ldquoassumed inherent sensorrdquo is constructed and its left-invertible is validated. The artificial neural network (ANN) left-inversion flux estimator is composed of two relatively independent parts - a static ANN used to approximate the complex nonlinear function and several differentiators used to represent its dynamic behaviors, so that the ANN left-inversion is a special kind of dynamic ANN in essence. The performance of the proposed algorithm is tested through simulation and experiment, proving good behavior in both transient and steady-state operating conditions.