Permanent Magnet Synchronous Motor Control Based on Retina Neural Network

Author

Yang, Junyou ; Wu, Yuliang ; Yu, Yanjun ; Zhao, Wenzeng

Author_Institution

Key Lab. of Special Electr. Machine & High Voltage Apparatus, Shenyang Univ. of Technol., Shenyang, China

fYear

2010

fDate

7-9 Nov. 2010

Firstpage

1

Lastpage

4

Abstract

A novel neural network, retina neural network (RNN) is put forward, and its definition, network structure, parameters, and characteristic are presented. After training it using a set of samples, an ideal training waveform is obtained, which is a great guide for future research. Moreover, a model of permanent magnet synchronous motor (PMSM) PI controller is constructed based on RNN to test drive performances. Finally, the simulation results show that the network convergence is rational and its rapidity and real-time performance are attractive. RNN has a simple structure and weight adjustment. The RNN application in future research to PMSM drive area is forecasted.

Keywords

PI control; machine control; neural nets; permanent magnet motors; PI controller; PMSM; RNN; network structure; permanent magnet synchronous motor control; retina neural network; structure adjustment; weight adjustment; Artificial neural networks; Mathematical model; Real time systems; Recurrent neural networks; Retina; Torque; Training;

fLanguage

English

Publisher

ieee

Conference_Titel

E-Product E-Service and E-Entertainment (ICEEE), 2010 International Conference on

Conference_Location

Henan

Print_ISBN

978-1-4244-7159-1

Type

conf

DOI

10.1109/ICEEE.2010.5661508

Filename

5661508