Control of a loaded induction machine using a feedforward neural network

Neural networks have been the subject of great interest in the control field. They seem to offer good ability to solve complex tasks. In this paper, some results of using a neural network for the nonlinear control of an induction machine's speed are presented. The neural controller is a feedfor...

Full description

Saved in:
Bibliographic Details
Published in:International journal of systems science Vol. 27; no. 12; pp. 1287 - 1295
Main Authors: CHTOUROU, MOHAMED, DERBEL, NABIL, KAMOUN, MOHAMED BEN ALI
Format: Journal Article
Language:English
Published: London Taylor & Francis Group 01.12.1996
Taylor & Francis
Subjects:
Applied sciences
Artificial intelligence
Computer science; control theory; systems
Connectionism. Neural networks
Electrical engineering. Electrical power engineering
Electrical machines
Exact sciences and technology
Regulation and control
Simulation
Induction machine
Control synthesis
Integrator
Speed control
Perturbation
Neural network
Feedforward
Non linear system
Learning algorithm
ISSN:0020-7721, 1464-5319
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Neural networks have been the subject of great interest in the control field. They seem to offer good ability to solve complex tasks. In this paper, some results of using a neural network for the nonlinear control of an induction machine's speed are presented. The neural controller is a feedforward neural network identified off-line. The backpropagation learning algorithm has been used for the off-line identification of the plant inverse neural model which provides the control action. Simulations under measurement noise and environmental condition variations have been investigated and comparison of performance has been made with an adaptive neural controller. The obtained results show the efficiency and the implementation simplicity of the presented strategy
ISSN:0020-7721
1464-5319
DOI:10.1080/00207729608929335