A neural network lab experiment

Robert Lynn Mueller

Research output: Contribution to journalArticle

Abstract

Neural networks are becoming widely used in complex control problems. Many academic exercises approach neural network applications using only software simulations; however, simulations alone do not give students a full appreciation of the power and complexity of neural network-based controls. This paper describes a laboratory experiment that uses a temperature and airflow process simulator to demonstrate neural network control applications. The simulator is fundamentally a temperature controller in which large-scale changes in forced airflow produce significant changes in heat load. The initial labs use PID control techniques to solve the temperature control problem and to demonstrate the problem that PID controllers have with large disturbances. The following labs address the same problem using a neural network control strategy. An actual neural network controller is built and used to perform the same temperature control as the classical PID system. Capabilities and drawbacks of neural network control are demonstrated.

Original languageEnglish (US)
Pages (from-to)753-763
Number of pages11
JournalASEE Annual Conference Proceedings
StatePublished - 2001

Fingerprint

Neural networks
Experiments
Temperature control
Controllers
Simulators
Three term control systems
Thermal load
Students
Temperature

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Mueller, Robert Lynn. / A neural network lab experiment. In: ASEE Annual Conference Proceedings. 2001 ; pp. 753-763.
@article{81c05846c4924b5184338af81b706d44,
title = "A neural network lab experiment",
abstract = "Neural networks are becoming widely used in complex control problems. Many academic exercises approach neural network applications using only software simulations; however, simulations alone do not give students a full appreciation of the power and complexity of neural network-based controls. This paper describes a laboratory experiment that uses a temperature and airflow process simulator to demonstrate neural network control applications. The simulator is fundamentally a temperature controller in which large-scale changes in forced airflow produce significant changes in heat load. The initial labs use PID control techniques to solve the temperature control problem and to demonstrate the problem that PID controllers have with large disturbances. The following labs address the same problem using a neural network control strategy. An actual neural network controller is built and used to perform the same temperature control as the classical PID system. Capabilities and drawbacks of neural network control are demonstrated.",
author = "Mueller, {Robert Lynn}",
year = "2001",
language = "English (US)",
pages = "753--763",
journal = "ASEE Annual Conference Proceedings",
issn = "0190-1052",

}

A neural network lab experiment. / Mueller, Robert Lynn.

In: ASEE Annual Conference Proceedings, 2001, p. 753-763.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A neural network lab experiment

AU - Mueller, Robert Lynn

PY - 2001

Y1 - 2001

N2 - Neural networks are becoming widely used in complex control problems. Many academic exercises approach neural network applications using only software simulations; however, simulations alone do not give students a full appreciation of the power and complexity of neural network-based controls. This paper describes a laboratory experiment that uses a temperature and airflow process simulator to demonstrate neural network control applications. The simulator is fundamentally a temperature controller in which large-scale changes in forced airflow produce significant changes in heat load. The initial labs use PID control techniques to solve the temperature control problem and to demonstrate the problem that PID controllers have with large disturbances. The following labs address the same problem using a neural network control strategy. An actual neural network controller is built and used to perform the same temperature control as the classical PID system. Capabilities and drawbacks of neural network control are demonstrated.

AB - Neural networks are becoming widely used in complex control problems. Many academic exercises approach neural network applications using only software simulations; however, simulations alone do not give students a full appreciation of the power and complexity of neural network-based controls. This paper describes a laboratory experiment that uses a temperature and airflow process simulator to demonstrate neural network control applications. The simulator is fundamentally a temperature controller in which large-scale changes in forced airflow produce significant changes in heat load. The initial labs use PID control techniques to solve the temperature control problem and to demonstrate the problem that PID controllers have with large disturbances. The following labs address the same problem using a neural network control strategy. An actual neural network controller is built and used to perform the same temperature control as the classical PID system. Capabilities and drawbacks of neural network control are demonstrated.

UR - http://www.scopus.com/inward/record.url?scp=8744228940&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=8744228940&partnerID=8YFLogxK

M3 - Article

SP - 753

EP - 763

JO - ASEE Annual Conference Proceedings

JF - ASEE Annual Conference Proceedings

SN - 0190-1052

ER -