Hybrid controller using a neural network for a PM synchronous servo-motor drive

F. J. Lin, R. J. Wai

Research output: Contribution to journalArticlepeer-review

35 Scopus citations

Abstract

A permanent magnet (PM) synchronous servo-motor drive with a hybrid controller, which combines the advantages of the integral-proportional (IP) controller and the neural network, is introduced for both speed and position control. First, the IP speed and position controllers are designed according to the estimated plant model to match the time-domain command tracking specifications. Then the resulting closed-loop tracking transfer function of the speed-control system is used as the reference model, and an adaptive signal generated from the neural-network controller, whose connective weights are trained on-line using the proposed delta adaptation law according to the modelfollowing error of the outputs, is added to the speed-control system to preserve a favourable model-fojlowing characteristic under various operating conditions. To demonstrate the effectiveness of the proposed hybrid controller, the control scheme is also implemented for the position-control system.

Original languageEnglish
Pages (from-to)223-230
Number of pages8
JournalIEE Proceedings: Electric Power Applications
Volume145
Issue number3
DOIs
StatePublished - 1998

Keywords

  • Integral-proportional controller
  • Neural network
  • Synchronous servo-motor drive

Fingerprint

Dive into the research topics of 'Hybrid controller using a neural network for a PM synchronous servo-motor drive'. Together they form a unique fingerprint.

Cite this