FPGA-based computed force control system using Elman neural network for linear ultrasonic motor

Faa Jeng Lin, Ying Chih Hung, Syuan Yi Chen

Research output: Contribution to journalArticle

55 Citations (Scopus)

Abstract

A field-programmable gate array (FPGA)-based computed force control system using an Elman neural network (ENN) is proposed to control the mover position of a linear ultrasonic motor (LUSM) in this paper. First, the structure and operating principle of the LUSM are introduced. Then, the dynamics of the LUSM mechanism with the introduction of a lumped uncertainty, which include the friction force, are derived. Since the dynamic characteristics and motor parameters of the LUSM are nonlinear and time varying, a computed force control system using ENN is designed to improve the control performance for the tracking of various reference trajectories. The ENN with both online learning and excellent approximation capabilities is employed to estimate a nonlinear function including the lumped uncertainty of the moving table mechanism. Moreover, the Lyapunov stability theorem and the projection algorithm are adopted to ensure the stability of the control system and the convergence of the ENN. Furthermore, an FPGA chip is adopted to implement the developed control algorithm for possible low-cost and high-performance industrial applications. The experimental results show that excellent positioning and tracking performance are achieved, and the robustness to parameter variations and friction force can be obtained as well using the proposed control system.

Original languageEnglish
Pages (from-to)1238-1253
Number of pages16
JournalIEEE Transactions on Industrial Electronics
Volume56
Issue number4
DOIs
Publication statusPublished - 2009 May 13

Keywords

  • Computed force control
  • Elman neural network (ENN)
  • Field-programmable gate array (FPGA)
  • Linear ultrasonic motor (LUSM)

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'FPGA-based computed force control system using Elman neural network for linear ultrasonic motor'. Together they form a unique fingerprint.

Cite this