Neural network based high efficiency drive for interior permanent magnet synchronous motors compensating EMF constant variation

Author

Urasaki, Naomitsu ; Senjyu, Tomonobu ; Uezato, Katsumi

Author_Institution

Univ. of the Ryukyus, Japan

Volume

3

fYear

2002

fDate

2002

Firstpage

1273

Abstract

An optimum d-axis current makes na interior permanent magnet synchronous motor (IPMSM) drive on maximum efficiency. However, the optimum d-axis current cannot be computed in real-time because the calculation includes the cube root. In this paper, a neural network based high efficiency drive strategy for IPMSM is presented. The neural network is employed as an identifier to determine the optimum d-axis current. The neural network can determine the optimum d-axis current in real-time. Furthermore, the accuracy is hardly degraded irrespective of the variation of the EMF constant. Simulation results confirm the validity of the proposed approach

Keywords

compensation; electric current control; losses; machine control; neurocontrollers; optimal control; permanent magnet motors; synchronous motor drives; EMF constant variation compensation; PI controller; cube root; current control; high efficiency drive; interior permanent magnet synchronous motors; iron loss; maximum efficiency; neural network; optimum d-axis current; speed control; Copper; Couplings; Degradation; Equivalent circuits; Iron; Magnetic flux; Neural networks; Permanent magnet motors; Synchronous motors; Voltage;

fLanguage

English

Publisher

ieee

Conference_Titel

Power Conversion Conference, 2002. PCC-Osaka 2002. Proceedings of the

Conference_Location

Osaka

Print_ISBN

0-7803-7156-9

Type

conf

DOI

10.1109/PCC.2002.998156

Filename

998156