Robust Sugeno type adaptive fuzzy neural network backstepping control for two-axis motion control system

Faa Jeng Lin, Po Huan Chou, Po Hung Shen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

A robust Sugeno type adaptive fuzzy neural network (RSAFNN) backstepping control for a two-axis motion control system is proposed in this paper. The adopted two-axis motion control system is composed of two permanent magnet linear synchronous motors (PMLSMs). The single-axis motion dynamics with the introduction of a lumped uncertainty, which includes parameter variations, external disturbances, cross coupled interference between the two PMLSMs and fiction force, is derived first. Then, a backstepping control approach is proposed to compensate the lumped uncertainty occurred in the two-axis motion control system. Moreover, to improve the control performance in the tracking of the reference contours, a RSAFNN backstepping control is proposed where a Sugeno type adaptive fuzzy neural networks (SAFNN) is employed to estimate the lumped uncertainty directly. Furthermore, the proposed control algorithms are implemented in a TMS320C32 DSP-based control computer.

Original languageEnglish
Title of host publication4th IET International Conference on Power Electronics, Machines and Drives, PEMD 2008
Pages411-415
Number of pages5
Edition538 CP
DOIs
StatePublished - 2008
Event4th IET International Conference on Power Electronics, Machines and Drives, PEMD 2008 - York, United Kingdom
Duration: 2 Apr 20084 Apr 2008

Publication series

NameIET Conference Publications
Number538 CP

Conference

Conference4th IET International Conference on Power Electronics, Machines and Drives, PEMD 2008
Country/TerritoryUnited Kingdom
CityYork
Period2/04/084/04/08

Keywords

  • Backstepping control
  • Permanent magnet linear synchronous motor
  • Sugeno type adaptive fuzzy neural network
  • X-Y table

Fingerprint

Dive into the research topics of 'Robust Sugeno type adaptive fuzzy neural network backstepping control for two-axis motion control system'. Together they form a unique fingerprint.

Cite this