WSEAS Transactions on Systems and Control
Print ISSN: 1991-8763, E-ISSN: 2224-2856
Volume 13, 2018
An Improved Neural Network SC_MRAS Speed Observer in Sensorless Control for Six Phase Induction Drives
Authors: , ,
Abstract: During the recent decades there has been considerable development of sensorless vector controlled SPIM drives for high performance industrial applications. Sensorless drives have been successfully applied for medium and high speed operation, however, at low and zero speed operation, the instability and the poor performance of observers is still always a large challenge. In this paper, a novel Stator Current Based Model Reference Adaptive System (SC_MRAS) speed observer is proposed to improve the performance of the MRAS speed observer, especially at low speed region. In the new MRAS method, a two-layer linear Neural Network (NN), which has been trained online by means of an Ordinary Least quares (OLS) algorithm, is used as an adaptive model to estimate the stator current. The proposed algorithm is less complicated, reduce computational effort, the proposed observer are quicker convergence in speed estimation. It can ensure that the whole drive system achieves faster satisfactory torque and speed control and strong robustness, especially at low and zero speed region. Beside the adaptive model of the proposed scheme is employed in prediction mode also is a new point to make the proposed observer operate better accuracy and stability both in transient and steady-state operation, the dynamic performance is significantly improved. In this proposed, the rotor flux, which is needed for the stator current estimation of the adaptive model, is identifier by the Voltage Model (VM). Detailed simulations and experimental tests are carried out to investigate the performance of the proposed schemes when compared to the BPN MRAS. The results presented for the new scheme show the great improvement in the performance of the MRAS observer in sensorless modes of operation, especially at low and zero speed.
Search Articles
Pages: 364-374
WSEAS Transactions on Systems and Control, ISSN / E-ISSN: 1991-8763 / 2224-2856, Volume 13, 2018, Art. #39