Optimization Design of Wavelet Network for Estimation of Flux and Torque in Induction Motor Control System

Abstract

A novel estimation method of flux and torque based on wavelet network is proposed in direct torque control system. The input nodes of the WN are the current error and the change in the current error and the output node of the WN is the stator resistance error, which can obtain the accurate estimation value. By means of enough training samples, the improved least squares algorithm is used to fulfill the network structure and parameter initialization. The wavelet transform technique can decompose the original signal into several other signals with different levels of resolution. From these decomposed signals, the original time domain signal can be recovered without losing any information. Once the instants are detected, the accurate stator flux vector and electromagnetic torque are acquired by the parameter estimator, which makes the direct torque control applicable in the low speed region, optimizing the inverter control strategy. The simulation results show that the proposed method is effective for estimation of flux and torque in induction motor control system.