No Cover Image

Journal article 696 views

A Vary-Parameter Convergence-Accelerated Recurrent Neural Network for Online Solving Dynamic Matrix Pseudoinverse and its Robot Application

Xiaoxiao Li, Shuai Li Orcid Logo, Zhihao Xu, Xuefeng Zhou

Neural Processing Letters, Volume: 53, Issue: 2, Pages: 1287 - 1304

Swansea University Author: Shuai Li Orcid Logo

Full text not available from this repository: check for access using links below.

Check full text

DOI (Published version): 10.1007/s11063-021-10440-x

Abstract

Among this study, a vary-parameter convergence-accelerated neural network (VPCANN) model is generalized to solving dynamic matrix pseudoinverse, which can achieve super exponential convergence and noise-resistant, compared to the traditional Zhang neural network (ZNN) designed for dynamic problems....

Full description

Published in: Neural Processing Letters
ISSN: 1370-4621 1573-773X
Published: Springer Science and Business Media LLC 2021
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa56362
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2021-03-03T09:11:10Z
last_indexed 2021-06-10T03:21:53Z
id cronfa56362
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2021-06-09T15:08:55.2790643</datestamp><bib-version>v2</bib-version><id>56362</id><entry>2021-03-03</entry><title>A Vary-Parameter Convergence-Accelerated Recurrent Neural Network for Online Solving Dynamic Matrix Pseudoinverse and its Robot Application</title><swanseaauthors><author><sid>42ff9eed09bcd109fbbe484a0f99a8a8</sid><ORCID>0000-0001-8316-5289</ORCID><firstname>Shuai</firstname><surname>Li</surname><name>Shuai Li</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2021-03-03</date><deptcode>MECH</deptcode><abstract>Among this study, a vary-parameter convergence-accelerated neural network (VPCANN) model is generalized to solving dynamic matrix pseudoinverse, which can achieve super exponential convergence and noise-resistant, compared to the traditional Zhang neural network (ZNN) designed for dynamic problems. Simulative experiments reveal that the neural state solutions synthesized by the VPCANN can quickly approach to the theoretical pseudoinverse. Moreover, based on three types of noise disturbance including constant noise, random noise and dynamic noise, comparisons between the VPCANN and ZNN model are also investigated, verifying noise-resistant of the VPCANN model is better than the ZNN. In addition, to show the potential application of the VPCANN in practice, the kinematic motion planning of a six-links robot manipulator is considered, further substantiating the efficacy of the VPCANN in the dynamic matrix pseudoinverse.</abstract><type>Journal Article</type><journal>Neural Processing Letters</journal><volume>53</volume><journalNumber>2</journalNumber><paginationStart>1287</paginationStart><paginationEnd>1304</paginationEnd><publisher>Springer Science and Business Media LLC</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>1370-4621</issnPrint><issnElectronic>1573-773X</issnElectronic><keywords>Zhang neural network; Varying-parameter convergence-accelerated neural network; Noise-resistant; Dynamic matrix pseudoinverse</keywords><publishedDay>1</publishedDay><publishedMonth>4</publishedMonth><publishedYear>2021</publishedYear><publishedDate>2021-04-01</publishedDate><doi>10.1007/s11063-021-10440-x</doi><url/><notes/><college>COLLEGE NANME</college><department>Mechanical Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MECH</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2021-06-09T15:08:55.2790643</lastEdited><Created>2021-03-03T09:08:32.9596505</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering</level></path><authors><author><firstname>Xiaoxiao</firstname><surname>Li</surname><order>1</order></author><author><firstname>Shuai</firstname><surname>Li</surname><orcid>0000-0001-8316-5289</orcid><order>2</order></author><author><firstname>Zhihao</firstname><surname>Xu</surname><order>3</order></author><author><firstname>Xuefeng</firstname><surname>Zhou</surname><order>4</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling 2021-06-09T15:08:55.2790643 v2 56362 2021-03-03 A Vary-Parameter Convergence-Accelerated Recurrent Neural Network for Online Solving Dynamic Matrix Pseudoinverse and its Robot Application 42ff9eed09bcd109fbbe484a0f99a8a8 0000-0001-8316-5289 Shuai Li Shuai Li true false 2021-03-03 MECH Among this study, a vary-parameter convergence-accelerated neural network (VPCANN) model is generalized to solving dynamic matrix pseudoinverse, which can achieve super exponential convergence and noise-resistant, compared to the traditional Zhang neural network (ZNN) designed for dynamic problems. Simulative experiments reveal that the neural state solutions synthesized by the VPCANN can quickly approach to the theoretical pseudoinverse. Moreover, based on three types of noise disturbance including constant noise, random noise and dynamic noise, comparisons between the VPCANN and ZNN model are also investigated, verifying noise-resistant of the VPCANN model is better than the ZNN. In addition, to show the potential application of the VPCANN in practice, the kinematic motion planning of a six-links robot manipulator is considered, further substantiating the efficacy of the VPCANN in the dynamic matrix pseudoinverse. Journal Article Neural Processing Letters 53 2 1287 1304 Springer Science and Business Media LLC 1370-4621 1573-773X Zhang neural network; Varying-parameter convergence-accelerated neural network; Noise-resistant; Dynamic matrix pseudoinverse 1 4 2021 2021-04-01 10.1007/s11063-021-10440-x COLLEGE NANME Mechanical Engineering COLLEGE CODE MECH Swansea University 2021-06-09T15:08:55.2790643 2021-03-03T09:08:32.9596505 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering Xiaoxiao Li 1 Shuai Li 0000-0001-8316-5289 2 Zhihao Xu 3 Xuefeng Zhou 4
title A Vary-Parameter Convergence-Accelerated Recurrent Neural Network for Online Solving Dynamic Matrix Pseudoinverse and its Robot Application
spellingShingle A Vary-Parameter Convergence-Accelerated Recurrent Neural Network for Online Solving Dynamic Matrix Pseudoinverse and its Robot Application
Shuai Li
title_short A Vary-Parameter Convergence-Accelerated Recurrent Neural Network for Online Solving Dynamic Matrix Pseudoinverse and its Robot Application
title_full A Vary-Parameter Convergence-Accelerated Recurrent Neural Network for Online Solving Dynamic Matrix Pseudoinverse and its Robot Application
title_fullStr A Vary-Parameter Convergence-Accelerated Recurrent Neural Network for Online Solving Dynamic Matrix Pseudoinverse and its Robot Application
title_full_unstemmed A Vary-Parameter Convergence-Accelerated Recurrent Neural Network for Online Solving Dynamic Matrix Pseudoinverse and its Robot Application
title_sort A Vary-Parameter Convergence-Accelerated Recurrent Neural Network for Online Solving Dynamic Matrix Pseudoinverse and its Robot Application
author_id_str_mv 42ff9eed09bcd109fbbe484a0f99a8a8
author_id_fullname_str_mv 42ff9eed09bcd109fbbe484a0f99a8a8_***_Shuai Li
author Shuai Li
author2 Xiaoxiao Li
Shuai Li
Zhihao Xu
Xuefeng Zhou
format Journal article
container_title Neural Processing Letters
container_volume 53
container_issue 2
container_start_page 1287
publishDate 2021
institution Swansea University
issn 1370-4621
1573-773X
doi_str_mv 10.1007/s11063-021-10440-x
publisher Springer Science and Business Media LLC
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 Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering
document_store_str 0
active_str 0
description Among this study, a vary-parameter convergence-accelerated neural network (VPCANN) model is generalized to solving dynamic matrix pseudoinverse, which can achieve super exponential convergence and noise-resistant, compared to the traditional Zhang neural network (ZNN) designed for dynamic problems. Simulative experiments reveal that the neural state solutions synthesized by the VPCANN can quickly approach to the theoretical pseudoinverse. Moreover, based on three types of noise disturbance including constant noise, random noise and dynamic noise, comparisons between the VPCANN and ZNN model are also investigated, verifying noise-resistant of the VPCANN model is better than the ZNN. In addition, to show the potential application of the VPCANN in practice, the kinematic motion planning of a six-links robot manipulator is considered, further substantiating the efficacy of the VPCANN in the dynamic matrix pseudoinverse.
published_date 2021-04-01T04:11:16Z
_version_ 1763753775466545152
score 11.036706

Similar Items