No Cover Image

Journal article 759 views 189 downloads

Deterministic learning enhanced neutral network control of unmanned helicopter

Yiming Jiang, Chenguang Yang, Shi-lu Dai, Beibei Ren

International Journal of Advanced Robotic Systems, Volume: 13, Issue: 6, Pages: 1 - 12

Swansea University Author: Chenguang Yang

Check full text

DOI (Published version): 10.1177/1729881416671118

Abstract

In this article, a neural network-based tracking controller is developed for an unmanned helicopter system with guaranteed global stability in the presence of uncertain system dynamics. Due to the coupling and modeling uncertainties of the helicopter systems, neutral networks approximation technique...

Full description

Published in: International Journal of Advanced Robotic Systems
ISSN: 1729-8814 1729-8814
Published: 2016
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa31614
first_indexed 2017-01-11T15:58:38Z
last_indexed 2018-02-09T05:18:43Z
id cronfa31614
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2017-07-07T15:31:19.3316883</datestamp><bib-version>v2</bib-version><id>31614</id><entry>2017-01-11</entry><title>Deterministic learning enhanced neutral network control of unmanned helicopter</title><swanseaauthors><author><sid>d2a5024448bfac00a9b3890a8404380b</sid><ORCID/><firstname>Chenguang</firstname><surname>Yang</surname><name>Chenguang Yang</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2017-01-11</date><abstract>In this article, a neural network-based tracking controller is developed for an unmanned helicopter system with guaranteed global stability in the presence of uncertain system dynamics. Due to the coupling and modeling uncertainties of the helicopter systems, neutral networks approximation techniques are employed to compensate the unknown dynamics of each subsystem. In order to extend the semiglobal stability achieved by conventional neural control to global stability, a switching mechanism is also integrated into the control design, such that the resulted neural controller is always valid without any concern on either initial conditions or range of state variables. In addition, deterministic learning is applied to the neutral network learning control, such that the adaptive neutral networks are able to store the learned knowledge that could be reused to construct neutral network controller with improved control performance. Simulation studies are carried out on a helicopter model to illustrate the effectiveness of the proposed control design.</abstract><type>Journal Article</type><journal>International Journal of Advanced Robotic Systems</journal><volume>13</volume><journalNumber>6</journalNumber><paginationStart>1</paginationStart><paginationEnd>12</paginationEnd><publisher/><issnPrint>1729-8814</issnPrint><issnElectronic>1729-8814</issnElectronic><keywords/><publishedDay>31</publishedDay><publishedMonth>12</publishedMonth><publishedYear>2016</publishedYear><publishedDate>2016-12-31</publishedDate><doi>10.1177/1729881416671118</doi><url/><notes/><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><apcterm/><lastEdited>2017-07-07T15:31:19.3316883</lastEdited><Created>2017-01-11T11:08:47.9561210</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Engineering and Applied Sciences - Uncategorised</level></path><authors><author><firstname>Yiming</firstname><surname>Jiang</surname><order>1</order></author><author><firstname>Chenguang</firstname><surname>Yang</surname><orcid/><order>2</order></author><author><firstname>Shi-lu</firstname><surname>Dai</surname><order>3</order></author><author><firstname>Beibei</firstname><surname>Ren</surname><order>4</order></author></authors><documents><document><filename>0031614-11012017111037.pdf</filename><originalFilename>jiang2016v2.pdf</originalFilename><uploaded>2017-01-11T11:10:37.0030000</uploaded><type>Output</type><contentLength>436236</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><embargoDate>2017-01-11T00:00:00.0000000</embargoDate><copyrightCorrect>false</copyrightCorrect></document></documents><OutputDurs/></rfc1807>
spelling 2017-07-07T15:31:19.3316883 v2 31614 2017-01-11 Deterministic learning enhanced neutral network control of unmanned helicopter d2a5024448bfac00a9b3890a8404380b Chenguang Yang Chenguang Yang true false 2017-01-11 In this article, a neural network-based tracking controller is developed for an unmanned helicopter system with guaranteed global stability in the presence of uncertain system dynamics. Due to the coupling and modeling uncertainties of the helicopter systems, neutral networks approximation techniques are employed to compensate the unknown dynamics of each subsystem. In order to extend the semiglobal stability achieved by conventional neural control to global stability, a switching mechanism is also integrated into the control design, such that the resulted neural controller is always valid without any concern on either initial conditions or range of state variables. In addition, deterministic learning is applied to the neutral network learning control, such that the adaptive neutral networks are able to store the learned knowledge that could be reused to construct neutral network controller with improved control performance. Simulation studies are carried out on a helicopter model to illustrate the effectiveness of the proposed control design. Journal Article International Journal of Advanced Robotic Systems 13 6 1 12 1729-8814 1729-8814 31 12 2016 2016-12-31 10.1177/1729881416671118 COLLEGE NANME COLLEGE CODE Swansea University 2017-07-07T15:31:19.3316883 2017-01-11T11:08:47.9561210 Faculty of Science and Engineering School of Engineering and Applied Sciences - Uncategorised Yiming Jiang 1 Chenguang Yang 2 Shi-lu Dai 3 Beibei Ren 4 0031614-11012017111037.pdf jiang2016v2.pdf 2017-01-11T11:10:37.0030000 Output 436236 application/pdf Version of Record true 2017-01-11T00:00:00.0000000 false
title Deterministic learning enhanced neutral network control of unmanned helicopter
spellingShingle Deterministic learning enhanced neutral network control of unmanned helicopter
Chenguang Yang
title_short Deterministic learning enhanced neutral network control of unmanned helicopter
title_full Deterministic learning enhanced neutral network control of unmanned helicopter
title_fullStr Deterministic learning enhanced neutral network control of unmanned helicopter
title_full_unstemmed Deterministic learning enhanced neutral network control of unmanned helicopter
title_sort Deterministic learning enhanced neutral network control of unmanned helicopter
author_id_str_mv d2a5024448bfac00a9b3890a8404380b
author_id_fullname_str_mv d2a5024448bfac00a9b3890a8404380b_***_Chenguang Yang
author Chenguang Yang
author2 Yiming Jiang
Chenguang Yang
Shi-lu Dai
Beibei Ren
format Journal article
container_title International Journal of Advanced Robotic Systems
container_volume 13
container_issue 6
container_start_page 1
publishDate 2016
institution Swansea University
issn 1729-8814
1729-8814
doi_str_mv 10.1177/1729881416671118
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Engineering and Applied Sciences - Uncategorised{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Engineering and Applied Sciences - Uncategorised
document_store_str 1
active_str 0
description In this article, a neural network-based tracking controller is developed for an unmanned helicopter system with guaranteed global stability in the presence of uncertain system dynamics. Due to the coupling and modeling uncertainties of the helicopter systems, neutral networks approximation techniques are employed to compensate the unknown dynamics of each subsystem. In order to extend the semiglobal stability achieved by conventional neural control to global stability, a switching mechanism is also integrated into the control design, such that the resulted neural controller is always valid without any concern on either initial conditions or range of state variables. In addition, deterministic learning is applied to the neutral network learning control, such that the adaptive neutral networks are able to store the learned knowledge that could be reused to construct neutral network controller with improved control performance. Simulation studies are carried out on a helicopter model to illustrate the effectiveness of the proposed control design.
published_date 2016-12-31T19:03:08Z
_version_ 1821342735764815872
score 11.04748

Similar Items