Publication detail

Inverse Model Approximation Using Iterative Method and Neural Networks with Practical Application for Unstable Nonlinear System Control

RAJCHL, M. BRABLC, M.

Original Title

Inverse Model Approximation Using Iterative Method and Neural Networks with Practical Application for Unstable Nonlinear System Control

English Title

Inverse Model Approximation Using Iterative Method and Neural Networks with Practical Application for Unstable Nonlinear System Control

Type

conference paper

Language

en

Original Abstract

In this paper a method for controlling and stabilizing an unstable nonlinear system using a NARX neural network is presented. It is difficult to design a common feedback controller or even perform system identification on unstable systems, more even so if these systems are nonlinear. To compensate for nonlinearity a feedforward controller is required. In this paper we present a method of estimating inverse model of the system for the feedforward controller using a NARX artificial neural network in an iterative approach which takes less time than methods commonly used and performs as good. This method is verified and tested on an educational model of magnetic levitation of steel ball. Both static and dynamic forms of the inverse model are presented and evaluated with positive results.

English abstract

In this paper a method for controlling and stabilizing an unstable nonlinear system using a NARX neural network is presented. It is difficult to design a common feedback controller or even perform system identification on unstable systems, more even so if these systems are nonlinear. To compensate for nonlinearity a feedforward controller is required. In this paper we present a method of estimating inverse model of the system for the feedforward controller using a NARX artificial neural network in an iterative approach which takes less time than methods commonly used and performs as good. This method is verified and tested on an educational model of magnetic levitation of steel ball. Both static and dynamic forms of the inverse model are presented and evaluated with positive results.

Keywords

nonlinear system, control, unstable, neural network, inverse model, magnetic levitation, PID, feedforward control

Released

23.01.2019

ISBN

978-80-214-5542-9

Book

PROCEEDINGS OF THE 2018 18TH INTERNATIONAL CONFERENCE ON MECHATRONICS - MECHATRONIKA (ME)

Pages from

209

Pages to

215

Pages count

7

Documents

BibTex


@inproceedings{BUT152523,
  author="Matej {Rajchl} and Martin {Brablc}",
  title="Inverse Model Approximation Using Iterative Method and Neural Networks with Practical Application for Unstable Nonlinear System Control",
  annote="In this paper a method for controlling and stabilizing an unstable nonlinear system using a NARX neural network is presented. It is difficult to design a common feedback controller or even perform system identification on unstable systems, more even so if these systems are nonlinear. To compensate for nonlinearity a feedforward controller is required. In this paper we present a method of estimating inverse model of the system for the feedforward controller using a NARX artificial neural network in an iterative approach which takes less time than methods commonly used and performs as good. This method is verified and tested on an
educational model of magnetic levitation of steel ball. Both static and dynamic forms of the inverse model are presented and evaluated with positive results.",
  booktitle="PROCEEDINGS OF THE 2018 18TH INTERNATIONAL CONFERENCE ON MECHATRONICS - MECHATRONIKA (ME)",
  chapter="152523",
  howpublished="online",
  year="2019",
  month="january",
  pages="209--215",
  type="conference paper"
}