A self-similar neural network for distributed vibration control

A self-similar neural network has been investigated for the control of flexible structures with unknown dynamics. The system model is approximated by a partially recurrent neural network. The network predicts the future state based on the current control command and a window of the past state. The c...

Full description

Saved in:
Bibliographic Details
Main Author: Long, T.W.
Format: Conference Proceeding
Language:English
Subjects:
Control systems
Current control
Flexible structures
Frequency
Neural networks
Optimal control
Recurrent neural networks
State estimation
Switches
Vibration control
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 3248 vol.4
container_issue
container_start_page 3243
container_title
container_volume ol. 4
creator Long, T.W.
description A self-similar neural network has been investigated for the control of flexible structures with unknown dynamics. The system model is approximated by a partially recurrent neural network. The network predicts the future state based on the current control command and a window of the past state. The controller, which is part of the system model, holds a copy of the system model. Thus the controller can compute the optimal control by using the estimation of all the future states within a look-ahead horizon. This ability to look ahead enables the controller to successfully attenuate vibrations generated by impulse, high frequency sine waves and random excitation. When an unfamiliar situation is encountered, the controller switches to exploration mode. During exploration, the learning rate is increased, and a low level of control is applied to stimulate the system without driving it out of bounds. Test cases show that the network resumed effective control after only a few seconds of exploration. This quick learning ability makes the controller suitable for systems having a wide range of operating conditions.< >
doi_str_mv 10.1109/CDC.1993.325803
format conference_proceeding
fullrecord <record><control><sourceid>proquest_6IE</sourceid><recordid>TN_cdi_proquest_miscellaneous_26212023</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>325803</ieee_id><sourcerecordid>26212023</sourcerecordid><originalsourceid>FETCH-LOGICAL-i203t-e31d3f8015a98f457a61f650e499271b00081dbddb1250e5be062e76e427a8b43</originalsourceid><addsrcrecordid>eNotUMFKxDAUDIigrD0Lnnry1pqXNG1ykqXqKix40XNJti8QTZs1SRX_3sI6DAwMwzAMIddAawCq7vqHvgaleM2ZkJSfkUJ1kq7kwJRkF6RI6YOuEEKCbC_J_bZM6G2V3OS8juWMS9R-lfwT4mdpQyxHl3J0Zsk4lt_ORJ1dmMtDmHMM_oqcW-0TFv-6Ie9Pj2_9c7V_3b30233lGOW5Qg4jt5KC0EraRnS6BdsKio1SrAOzLpIwmnE0wFZXGKQtw67FhnVamoZvyO2p9xjD14IpD5NLB_RezxiWNLCWAaOMr8GbU9Ah4nCMbtLxdzjdwf8AFi5URg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype><pqid>26212023</pqid></control><display><type>conference_proceeding</type><title>A self-similar neural network for distributed vibration control</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Long, T.W.</creator><creatorcontrib>Long, T.W.</creatorcontrib><description>A self-similar neural network has been investigated for the control of flexible structures with unknown dynamics. The system model is approximated by a partially recurrent neural network. The network predicts the future state based on the current control command and a window of the past state. The controller, which is part of the system model, holds a copy of the system model. Thus the controller can compute the optimal control by using the estimation of all the future states within a look-ahead horizon. This ability to look ahead enables the controller to successfully attenuate vibrations generated by impulse, high frequency sine waves and random excitation. When an unfamiliar situation is encountered, the controller switches to exploration mode. During exploration, the learning rate is increased, and a low level of control is applied to stimulate the system without driving it out of bounds. Test cases show that the network resumed effective control after only a few seconds of exploration. This quick learning ability makes the controller suitable for systems having a wide range of operating conditions.&lt; &gt;</description><identifier>ISBN: 9780780312982</identifier><identifier>ISBN: 0780312988</identifier><identifier>DOI: 10.1109/CDC.1993.325803</identifier><language>eng</language><publisher>IEEE</publisher><subject>Control systems ; Current control ; Flexible structures ; Frequency ; Neural networks ; Optimal control ; Recurrent neural networks ; State estimation ; Switches ; Vibration control</subject><ispartof>IEEE Decision and Control, 1993, 1993, Vol.ol. 4, p.3243-3248 vol.4</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/325803$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,314,780,784,789,790,2056,4048,4049,27923,27924,54919</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/325803$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Long, T.W.</creatorcontrib><title>A self-similar neural network for distributed vibration control</title><title>IEEE Decision and Control, 1993</title><addtitle>CDC</addtitle><description>A self-similar neural network has been investigated for the control of flexible structures with unknown dynamics. The system model is approximated by a partially recurrent neural network. The network predicts the future state based on the current control command and a window of the past state. The controller, which is part of the system model, holds a copy of the system model. Thus the controller can compute the optimal control by using the estimation of all the future states within a look-ahead horizon. This ability to look ahead enables the controller to successfully attenuate vibrations generated by impulse, high frequency sine waves and random excitation. When an unfamiliar situation is encountered, the controller switches to exploration mode. During exploration, the learning rate is increased, and a low level of control is applied to stimulate the system without driving it out of bounds. Test cases show that the network resumed effective control after only a few seconds of exploration. This quick learning ability makes the controller suitable for systems having a wide range of operating conditions.&lt; &gt;</description><subject>Control systems</subject><subject>Current control</subject><subject>Flexible structures</subject><subject>Frequency</subject><subject>Neural networks</subject><subject>Optimal control</subject><subject>Recurrent neural networks</subject><subject>State estimation</subject><subject>Switches</subject><subject>Vibration control</subject><isbn>9780780312982</isbn><isbn>0780312988</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>1993</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotUMFKxDAUDIigrD0Lnnry1pqXNG1ykqXqKix40XNJti8QTZs1SRX_3sI6DAwMwzAMIddAawCq7vqHvgaleM2ZkJSfkUJ1kq7kwJRkF6RI6YOuEEKCbC_J_bZM6G2V3OS8juWMS9R-lfwT4mdpQyxHl3J0Zsk4lt_ORJ1dmMtDmHMM_oqcW-0TFv-6Ie9Pj2_9c7V_3b30233lGOW5Qg4jt5KC0EraRnS6BdsKio1SrAOzLpIwmnE0wFZXGKQtw67FhnVamoZvyO2p9xjD14IpD5NLB_RezxiWNLCWAaOMr8GbU9Ah4nCMbtLxdzjdwf8AFi5URg</recordid><startdate>1993</startdate><enddate>1993</enddate><creator>Long, T.W.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>1993</creationdate><title>A self-similar neural network for distributed vibration control</title><author>Long, T.W.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i203t-e31d3f8015a98f457a61f650e499271b00081dbddb1250e5be062e76e427a8b43</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>1993</creationdate><topic>Control systems</topic><topic>Current control</topic><topic>Flexible structures</topic><topic>Frequency</topic><topic>Neural networks</topic><topic>Optimal control</topic><topic>Recurrent neural networks</topic><topic>State estimation</topic><topic>Switches</topic><topic>Vibration control</topic><toplevel>online_resources</toplevel><creatorcontrib>Long, T.W.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Long, T.W.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>A self-similar neural network for distributed vibration control</atitle><btitle>IEEE Decision and Control, 1993</btitle><stitle>CDC</stitle><date>1993</date><risdate>1993</risdate><volume>ol. 4</volume><spage>3243</spage><epage>3248 vol.4</epage><pages>3243-3248 vol.4</pages><isbn>9780780312982</isbn><isbn>0780312988</isbn><abstract>A self-similar neural network has been investigated for the control of flexible structures with unknown dynamics. The system model is approximated by a partially recurrent neural network. The network predicts the future state based on the current control command and a window of the past state. The controller, which is part of the system model, holds a copy of the system model. Thus the controller can compute the optimal control by using the estimation of all the future states within a look-ahead horizon. This ability to look ahead enables the controller to successfully attenuate vibrations generated by impulse, high frequency sine waves and random excitation. When an unfamiliar situation is encountered, the controller switches to exploration mode. During exploration, the learning rate is increased, and a low level of control is applied to stimulate the system without driving it out of bounds. Test cases show that the network resumed effective control after only a few seconds of exploration. This quick learning ability makes the controller suitable for systems having a wide range of operating conditions.&lt; &gt;</abstract><pub>IEEE</pub><doi>10.1109/CDC.1993.325803</doi></addata></record>
fulltext fulltext_linktorsrc
identifier ISBN: 9780780312982
ispartof IEEE Decision and Control, 1993, 1993, Vol.ol. 4, p.3243-3248 vol.4
issn
language eng
recordid cdi_proquest_miscellaneous_26212023
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Control systems
Current control
Flexible structures
Frequency
Neural networks
Optimal control
Recurrent neural networks
State estimation
Switches
Vibration control
title A self-similar neural network for distributed vibration control
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-11T19%3A33%3A04IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=A%20self-similar%20neural%20network%20for%20distributed%20vibration%20control&rft.btitle=IEEE%20Decision%20and%20Control,%201993&rft.au=Long,%20T.W.&rft.date=1993&rft.volume=ol.%204&rft.spage=3243&rft.epage=3248%20vol.4&rft.pages=3243-3248%20vol.4&rft.isbn=9780780312982&rft.isbn_list=0780312988&rft_id=info:doi/10.1109/CDC.1993.325803&rft_dat=%3Cproquest_6IE%3E26212023%3C/proquest_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i203t-e31d3f8015a98f457a61f650e499271b00081dbddb1250e5be062e76e427a8b43%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=26212023&rft_id=info:pmid/&rft_ieee_id=325803&rfr_iscdi=true