The addition of neural networks to the inner feedback path in order to improve on the use of pre-trained feed forward estimators

David Sanders; B. P Haynes; Giles Tewkesbury; I. J Stott

doi:10.1016/0378-4754(95)00093-3

The addition of neural networks to the inner feedback path in order to improve on the use of pre-trained feed forward estimators

David Sanders, B. P Haynes, Giles Tewkesbury, I. J Stott

Research output: Contribution to journal › Article › peer-review

Abstract

A learning control architecture which uses a multi-layer feed forward neural network with error back propagation is described. The architecture includes a feed forward estimator which is pre-trained and a feedback controller which continues to learn. The properties of the architectures are investigated through a series of experiments, and the application of the prototype adaptive controllers is described. To examine the performance of this controller, square wave demand signals are applied to the controller and the results are presented.

Original language	English
Pages (from-to)	461-472
Journal	Mathematics and Computers in Simulation
Volume	41
Issue number	5-6
DOIs	https://doi.org/10.1016/0378-4754(95)00093-3
Publication status	Published - Aug 1996

Keywords

Mathematics
neural networks
Simulation
Computers

Access to Document

10.1016/0378-4754(95)00093-3

http://www.sciencedirect.com/science/article/pii/0378475495000933

European Teleman project: Teleoperated vehicle system for remote inspection in hazardous environments - Sensor integration, fault tolerance and control systems for inspection.
Collie, A., Luk, B. L., Cooke, D., Virk, G., White, T., Sanders, D., Hewer, N., Chen, S., Billingsley, J., Urwin-Wright, S. D. & Bevan, N.
1/01/93 → 1/02/96
Project: Research
Using neural networks and fuzzy logic for control
Sanders, D., Haynes, B. P., Stott, I. & Tewkesbury, G.
24/03/90 → 16/03/93
Project: Research

Cite this

@article{493e85cc386249128e98b001ef71b5cb,

title = "The addition of neural networks to the inner feedback path in order to improve on the use of pre-trained feed forward estimators",

abstract = "A learning control architecture which uses a multi-layer feed forward neural network with error back propagation is described. The architecture includes a feed forward estimator which is pre-trained and a feedback controller which continues to learn. The properties of the architectures are investigated through a series of experiments, and the application of the prototype adaptive controllers is described. To examine the performance of this controller, square wave demand signals are applied to the controller and the results are presented.",

keywords = "Mathematics, neural networks , Simulation, Computers",

author = "David Sanders and Haynes, {B. P} and Giles Tewkesbury and Stott, {I. J}",

year = "1996",

month = aug,

doi = "10.1016/0378-4754(95)00093-3",

language = "English",

volume = "41",

pages = "461--472",

journal = "Mathematics and Computers in Simulation",

issn = "0378-4754",

publisher = "Elsevier",

number = "5-6",

}

TY - JOUR

T1 - The addition of neural networks to the inner feedback path in order to improve on the use of pre-trained feed forward estimators

AU - Sanders, David

AU - Haynes, B. P

AU - Tewkesbury, Giles

AU - Stott, I. J

PY - 1996/8

Y1 - 1996/8

N2 - A learning control architecture which uses a multi-layer feed forward neural network with error back propagation is described. The architecture includes a feed forward estimator which is pre-trained and a feedback controller which continues to learn. The properties of the architectures are investigated through a series of experiments, and the application of the prototype adaptive controllers is described. To examine the performance of this controller, square wave demand signals are applied to the controller and the results are presented.

AB - A learning control architecture which uses a multi-layer feed forward neural network with error back propagation is described. The architecture includes a feed forward estimator which is pre-trained and a feedback controller which continues to learn. The properties of the architectures are investigated through a series of experiments, and the application of the prototype adaptive controllers is described. To examine the performance of this controller, square wave demand signals are applied to the controller and the results are presented.

KW - Mathematics

KW - neural networks

KW - Simulation

KW - Computers

U2 - 10.1016/0378-4754(95)00093-3

DO - 10.1016/0378-4754(95)00093-3

M3 - Article

SN - 0378-4754

VL - 41

SP - 461

EP - 472

JO - Mathematics and Computers in Simulation

JF - Mathematics and Computers in Simulation

IS - 5-6

ER -

The addition of neural networks to the inner feedback path in order to improve on the use of pre-trained feed forward estimators

Abstract

Keywords

Access to Document

Fingerprint

Projects

European Teleman project: Teleoperated vehicle system for remote inspection in hazardous environments - Sensor integration, fault tolerance and control systems for inspection.

Using neural networks and fuzzy logic for control

Cite this