Neural network design with genetic learning for control of a single link flexible manipulator

Sandeep Jain, Pei Yuan Peng, Antonios Tzes, Farshad Khorrami

Research output: Contribution to journalArticle

Abstract

The application of neural networks for active control of lightly damped systems is considered in this article. The training process of the neural-network controller is based on the genetic learning algorithm. The schemes imitates nature's cleansing phenomena of natural selection and survival of the fittest to generate individual controllers with the best fitness values. It essentially incorporates an exhaustive search in the weight-space governed by the rituals of crossover and mutation to seek the optimum neural-network weights to satisfy certain performance criteria. Several appropriate modifications of the classical genetic algorithm for neural-network control purposes are discussed. The genetic-trained neural-network controller is applied for tip position tracking and vibration suppression of a single-link flexible arm. Simulation studies are presented to validate the effectiveness of the advocated algorithms.

Original languageEnglish (US)
Pages (from-to)135-151
Number of pages17
JournalJournal of Intelligent and Robotic Systems: Theory and Applications
Volume15
Issue number2
StatePublished - Feb 1996

Fingerprint

Flexible manipulators
Neural networks
Controllers
Genetic algorithms
Learning algorithms
Telecommunication links

ASJC Scopus subject areas

  • Artificial Intelligence
  • Control and Systems Engineering

Cite this

Neural network design with genetic learning for control of a single link flexible manipulator. / Jain, Sandeep; Peng, Pei Yuan; Tzes, Antonios; Khorrami, Farshad.

In: Journal of Intelligent and Robotic Systems: Theory and Applications, Vol. 15, No. 2, 02.1996, p. 135-151.

Research output: Contribution to journalArticle

@article{0c69016e890a441cbc6d8f453083d037,
title = "Neural network design with genetic learning for control of a single link flexible manipulator",
abstract = "The application of neural networks for active control of lightly damped systems is considered in this article. The training process of the neural-network controller is based on the genetic learning algorithm. The schemes imitates nature's cleansing phenomena of natural selection and survival of the fittest to generate individual controllers with the best fitness values. It essentially incorporates an exhaustive search in the weight-space governed by the rituals of crossover and mutation to seek the optimum neural-network weights to satisfy certain performance criteria. Several appropriate modifications of the classical genetic algorithm for neural-network control purposes are discussed. The genetic-trained neural-network controller is applied for tip position tracking and vibration suppression of a single-link flexible arm. Simulation studies are presented to validate the effectiveness of the advocated algorithms.",
author = "Sandeep Jain and Peng, {Pei Yuan} and Antonios Tzes and Farshad Khorrami",
year = "1996",
month = "2",
language = "English (US)",
volume = "15",
pages = "135--151",
journal = "Journal of Intelligent and Robotic Systems: Theory and Applications",
issn = "0921-0296",
publisher = "Springer Netherlands",
number = "2",

}

TY - JOUR

T1 - Neural network design with genetic learning for control of a single link flexible manipulator

AU - Jain, Sandeep

AU - Peng, Pei Yuan

AU - Tzes, Antonios

AU - Khorrami, Farshad

PY - 1996/2

Y1 - 1996/2

N2 - The application of neural networks for active control of lightly damped systems is considered in this article. The training process of the neural-network controller is based on the genetic learning algorithm. The schemes imitates nature's cleansing phenomena of natural selection and survival of the fittest to generate individual controllers with the best fitness values. It essentially incorporates an exhaustive search in the weight-space governed by the rituals of crossover and mutation to seek the optimum neural-network weights to satisfy certain performance criteria. Several appropriate modifications of the classical genetic algorithm for neural-network control purposes are discussed. The genetic-trained neural-network controller is applied for tip position tracking and vibration suppression of a single-link flexible arm. Simulation studies are presented to validate the effectiveness of the advocated algorithms.

AB - The application of neural networks for active control of lightly damped systems is considered in this article. The training process of the neural-network controller is based on the genetic learning algorithm. The schemes imitates nature's cleansing phenomena of natural selection and survival of the fittest to generate individual controllers with the best fitness values. It essentially incorporates an exhaustive search in the weight-space governed by the rituals of crossover and mutation to seek the optimum neural-network weights to satisfy certain performance criteria. Several appropriate modifications of the classical genetic algorithm for neural-network control purposes are discussed. The genetic-trained neural-network controller is applied for tip position tracking and vibration suppression of a single-link flexible arm. Simulation studies are presented to validate the effectiveness of the advocated algorithms.

UR - http://www.scopus.com/inward/record.url?scp=0030080921&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030080921&partnerID=8YFLogxK

M3 - Article

VL - 15

SP - 135

EP - 151

JO - Journal of Intelligent and Robotic Systems: Theory and Applications

JF - Journal of Intelligent and Robotic Systems: Theory and Applications

SN - 0921-0296

IS - 2

ER -