Neural Network based control of large structures

S. R. Vadali; T. Singh; A. J. Kurdila; J. L. Junkins

doi:10.1117/12.152819

Neural Network based control of large structures

S. R. Vadali
, T. Singh
, A. J. Kurdila
, J. L. Junkins

Department of Mechanical and Aerospace Engineering

Texas A&M University

Research output: Contribution to journal › Conference article › peer-review

2 Scopus citations

Abstract

Adaptive control of spacecraft and large structures using Radial Basis Function(RBF) based Artificial Neural Networks (ANN) is investigated. The centers of approximation of the RBFs are allowed to be dynamic in order to provide persistent excitation and a small window of approximation. Both state and time based RBFs are investigated for their ability to identify unmodeled and persistent effects. Integral feedback of the attitude seems necessary, especially when the initial estimates are poor, to eliminate steady state errors for pointing applications. Examples of motion-to-rest as well as tracking maneuvers and vibration suppression are presented.

Original language	English
Pages (from-to)	895-906
Number of pages	12
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	1917
DOIs	https://doi.org/10.1117/12.152819
State	Published - Sep 8 1993
Event	Smart Structures and Materials 1993: Smart Structures and Intelligent Systems - Albuquerque, United States Duration: Feb 1 1993 → Feb 4 1993

Access to Document

10.1117/12.152819

Cite this

@article{0f92d0b39c3245199591584ad7225e4e,

title = "Neural Network based control of large structures",

abstract = "Adaptive control of spacecraft and large structures using Radial Basis Function(RBF) based Artificial Neural Networks (ANN) is investigated. The centers of approximation of the RBFs are allowed to be dynamic in order to provide persistent excitation and a small window of approximation. Both state and time based RBFs are investigated for their ability to identify unmodeled and persistent effects. Integral feedback of the attitude seems necessary, especially when the initial estimates are poor, to eliminate steady state errors for pointing applications. Examples of motion-to-rest as well as tracking maneuvers and vibration suppression are presented.",

author = "Vadali, \{S. R.\} and T. Singh and Kurdila, \{A. J.\} and Junkins, \{J. L.\}",

note = "Publisher Copyright: {\textcopyright} 1993 SPIE. All rights reserved.; Smart Structures and Materials 1993: Smart Structures and Intelligent Systems ; Conference date: 01-02-1993 Through 04-02-1993",

year = "1993",

month = sep,

day = "8",

doi = "10.1117/12.152819",

language = "English",

volume = "1917",

pages = "895--906",

journal = "Proceedings of SPIE - The International Society for Optical Engineering",

issn = "0277-786X",

publisher = "SPIE",

}

TY - JOUR

T1 - Neural Network based control of large structures

AU - Vadali, S. R.

AU - Singh, T.

AU - Kurdila, A. J.

AU - Junkins, J. L.

PY - 1993/9/8

Y1 - 1993/9/8

N2 - Adaptive control of spacecraft and large structures using Radial Basis Function(RBF) based Artificial Neural Networks (ANN) is investigated. The centers of approximation of the RBFs are allowed to be dynamic in order to provide persistent excitation and a small window of approximation. Both state and time based RBFs are investigated for their ability to identify unmodeled and persistent effects. Integral feedback of the attitude seems necessary, especially when the initial estimates are poor, to eliminate steady state errors for pointing applications. Examples of motion-to-rest as well as tracking maneuvers and vibration suppression are presented.

AB - Adaptive control of spacecraft and large structures using Radial Basis Function(RBF) based Artificial Neural Networks (ANN) is investigated. The centers of approximation of the RBFs are allowed to be dynamic in order to provide persistent excitation and a small window of approximation. Both state and time based RBFs are investigated for their ability to identify unmodeled and persistent effects. Integral feedback of the attitude seems necessary, especially when the initial estimates are poor, to eliminate steady state errors for pointing applications. Examples of motion-to-rest as well as tracking maneuvers and vibration suppression are presented.

UR - https://www.scopus.com/pages/publications/84966575835

U2 - 10.1117/12.152819

DO - 10.1117/12.152819

M3 - Conference article

AN - SCOPUS:84966575835

SN - 0277-786X

VL - 1917

SP - 895

EP - 906

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

T2 - Smart Structures and Materials 1993: Smart Structures and Intelligent Systems

Y2 - 1 February 1993 through 4 February 1993

ER -

Neural Network based control of large structures

Abstract

Access to Document

Other files and links

Fingerprint

Cite this