Neural identification of dynamic systems on FPGA with improved PSO learning


Cavuslu M. A. , KARAKUZU C., KARAKAYA F.

APPLIED SOFT COMPUTING, vol.12, no.9, pp.2707-2718, 2012 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 12 Issue: 9
  • Publication Date: 2012
  • Doi Number: 10.1016/j.asoc.2012.03.022
  • Journal Name: APPLIED SOFT COMPUTING
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.2707-2718
  • Keywords: Artificial neural networks (ANN), Particle swarm optimization (PSO), FPGA, System identification, PARTICLE SWARM, HARDWARE IMPLEMENTATION, NETWORKS, ARCHITECTURE
  • Middle East Technical University Affiliated: Yes

Abstract

This work introduces hardware implementation of artificial neural networks (ANNs) with learning ability on field programmable gate array (FPGA) for dynamic system identification. The learning phase is accomplished by using the improved particle swarm optimization (PSO). The improved PSO is obtained by modifying the velocity update function. Adding an extra term to the velocity update function reduced the possibility of stucking in a local minimum. The results indicates that ANN, trained using improved PSO algorithm, converges faster and produces more accurate results with a little extra hardware utilization cost. (C) 2012 Elsevier B.V. All rights reserved.