Loading…

A conditional adversarial operator network prediction method for current fields in armature-rail contact surface

Linear propulsion electromagnetic energy equipment can convert electromagnetic energy to kinetic energy instantaneously and has many advantages, such as high kinetic energy, efficiency, precision, and strong controllability. It surpasses traditional mechanical and chemical energy methods, significan...

Full description

Saved in:
Bibliographic Details
Published in:Journal of computational design and engineering 2024-10, Vol.11 (5), p.284-302
Main Authors: Jin, Liang, Guo, Shaonan, Su, Haozhan, Song, Juheng, Jia, Yufang
Format: Article
Language:English
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites cdi_FETCH-LOGICAL-c160t-3f58642124be30c405bf5e27bd221d6454367e2bcbb3cbc7bd644e595a035fc83
container_end_page 302
container_issue 5
container_start_page 284
container_title Journal of computational design and engineering
container_volume 11
creator Jin, Liang
Guo, Shaonan
Su, Haozhan
Song, Juheng
Jia, Yufang
description Linear propulsion electromagnetic energy equipment can convert electromagnetic energy to kinetic energy instantaneously and has many advantages, such as high kinetic energy, efficiency, precision, and strong controllability. It surpasses traditional mechanical and chemical energy methods, significantly impacting various fields. Aiming at the numerical simulation method, which has problems with large computation volume and a long time of physical field simulation, the current field prediction method of linear propulsion electromagnetic energy equipment based on a Deep Generation Adversarial Operator Network is proposed. Firstly, deep operator network is combined with conditional generative adversarial network to obtain the knowledge-embedded conditional adversarial operator network (CGAONet) model. Then, Res-Transformer-Unet (RTUnet) is used as a branch network of CGAONet to establish the RTUnet-CGAONet model, and the current field method using a deep adversarial operator network is proposed. Finally, the finite element simulation model of the US public linear propulsion electromagnetic energy equipment calculation example is established to construct the simulation dataset from 1D excitation current value and time data to a 2D current field. The trained RTUnet-CGAONet model predicts the mean absolute percentage error of 2.94% in the 2D current field, and the model is minimally affected by the number of samples in the dataset. The results of this paper can achieve the second-level calculation of the current field under different excitation currents, which provides a new way of thinking for the analysis of dynamic characteristics of linear propulsion electromagnetic energy equipment.
doi_str_mv 10.1093/jcde/qwae082
format article
fullrecord <record><control><sourceid>crossref</sourceid><recordid>TN_cdi_crossref_primary_10_1093_jcde_qwae082</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>10_1093_jcde_qwae082</sourcerecordid><originalsourceid>FETCH-LOGICAL-c160t-3f58642124be30c405bf5e27bd221d6454367e2bcbb3cbc7bd644e595a035fc83</originalsourceid><addsrcrecordid>eNpNkMtOwzAURC0EElXpjg_wBxDqZ5ouq4qXVIkNrCM_roVLGodrh4q_pxFdsJrRzGgWh5Bbzu45W8vl3nlYfh0NsEZckJkQTVNppprLf_6aLHLeM8b4SkjG1zMybKhLvY8lpt501PhvwGwwnnwaAE1JSHsox4SfdEDw0U1LeoDykTwNp9aNiNAXGiJ0PtPYU4MHU0aECk3spvtiXKF5xGAc3JCrYLoMi7POyfvjw9v2udq9Pr1sN7vK8ZqVSgbd1EpwoSxI5hTTNmgQK-uF4L5WWsl6BcI6a6Wz7pTXSoFea8OkDq6Rc3L39-sw5YwQ2gHjweBPy1k7AWsnYO0ZmPwFDKZi-Q</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>A conditional adversarial operator network prediction method for current fields in armature-rail contact surface</title><source>Oxford Journals Open Access Collection</source><creator>Jin, Liang ; Guo, Shaonan ; Su, Haozhan ; Song, Juheng ; Jia, Yufang</creator><creatorcontrib>Jin, Liang ; Guo, Shaonan ; Su, Haozhan ; Song, Juheng ; Jia, Yufang</creatorcontrib><description>Linear propulsion electromagnetic energy equipment can convert electromagnetic energy to kinetic energy instantaneously and has many advantages, such as high kinetic energy, efficiency, precision, and strong controllability. It surpasses traditional mechanical and chemical energy methods, significantly impacting various fields. Aiming at the numerical simulation method, which has problems with large computation volume and a long time of physical field simulation, the current field prediction method of linear propulsion electromagnetic energy equipment based on a Deep Generation Adversarial Operator Network is proposed. Firstly, deep operator network is combined with conditional generative adversarial network to obtain the knowledge-embedded conditional adversarial operator network (CGAONet) model. Then, Res-Transformer-Unet (RTUnet) is used as a branch network of CGAONet to establish the RTUnet-CGAONet model, and the current field method using a deep adversarial operator network is proposed. Finally, the finite element simulation model of the US public linear propulsion electromagnetic energy equipment calculation example is established to construct the simulation dataset from 1D excitation current value and time data to a 2D current field. The trained RTUnet-CGAONet model predicts the mean absolute percentage error of 2.94% in the 2D current field, and the model is minimally affected by the number of samples in the dataset. The results of this paper can achieve the second-level calculation of the current field under different excitation currents, which provides a new way of thinking for the analysis of dynamic characteristics of linear propulsion electromagnetic energy equipment.</description><identifier>ISSN: 2288-5048</identifier><identifier>EISSN: 2288-5048</identifier><identifier>DOI: 10.1093/jcde/qwae082</identifier><language>eng</language><ispartof>Journal of computational design and engineering, 2024-10, Vol.11 (5), p.284-302</ispartof><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c160t-3f58642124be30c405bf5e27bd221d6454367e2bcbb3cbc7bd644e595a035fc83</cites><orcidid>0009-0008-7257-7286</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Jin, Liang</creatorcontrib><creatorcontrib>Guo, Shaonan</creatorcontrib><creatorcontrib>Su, Haozhan</creatorcontrib><creatorcontrib>Song, Juheng</creatorcontrib><creatorcontrib>Jia, Yufang</creatorcontrib><title>A conditional adversarial operator network prediction method for current fields in armature-rail contact surface</title><title>Journal of computational design and engineering</title><description>Linear propulsion electromagnetic energy equipment can convert electromagnetic energy to kinetic energy instantaneously and has many advantages, such as high kinetic energy, efficiency, precision, and strong controllability. It surpasses traditional mechanical and chemical energy methods, significantly impacting various fields. Aiming at the numerical simulation method, which has problems with large computation volume and a long time of physical field simulation, the current field prediction method of linear propulsion electromagnetic energy equipment based on a Deep Generation Adversarial Operator Network is proposed. Firstly, deep operator network is combined with conditional generative adversarial network to obtain the knowledge-embedded conditional adversarial operator network (CGAONet) model. Then, Res-Transformer-Unet (RTUnet) is used as a branch network of CGAONet to establish the RTUnet-CGAONet model, and the current field method using a deep adversarial operator network is proposed. Finally, the finite element simulation model of the US public linear propulsion electromagnetic energy equipment calculation example is established to construct the simulation dataset from 1D excitation current value and time data to a 2D current field. The trained RTUnet-CGAONet model predicts the mean absolute percentage error of 2.94% in the 2D current field, and the model is minimally affected by the number of samples in the dataset. The results of this paper can achieve the second-level calculation of the current field under different excitation currents, which provides a new way of thinking for the analysis of dynamic characteristics of linear propulsion electromagnetic energy equipment.</description><issn>2288-5048</issn><issn>2288-5048</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNpNkMtOwzAURC0EElXpjg_wBxDqZ5ouq4qXVIkNrCM_roVLGodrh4q_pxFdsJrRzGgWh5Bbzu45W8vl3nlYfh0NsEZckJkQTVNppprLf_6aLHLeM8b4SkjG1zMybKhLvY8lpt501PhvwGwwnnwaAE1JSHsox4SfdEDw0U1LeoDykTwNp9aNiNAXGiJ0PtPYU4MHU0aECk3spvtiXKF5xGAc3JCrYLoMi7POyfvjw9v2udq9Pr1sN7vK8ZqVSgbd1EpwoSxI5hTTNmgQK-uF4L5WWsl6BcI6a6Wz7pTXSoFea8OkDq6Rc3L39-sw5YwQ2gHjweBPy1k7AWsnYO0ZmPwFDKZi-Q</recordid><startdate>20241017</startdate><enddate>20241017</enddate><creator>Jin, Liang</creator><creator>Guo, Shaonan</creator><creator>Su, Haozhan</creator><creator>Song, Juheng</creator><creator>Jia, Yufang</creator><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0009-0008-7257-7286</orcidid></search><sort><creationdate>20241017</creationdate><title>A conditional adversarial operator network prediction method for current fields in armature-rail contact surface</title><author>Jin, Liang ; Guo, Shaonan ; Su, Haozhan ; Song, Juheng ; Jia, Yufang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c160t-3f58642124be30c405bf5e27bd221d6454367e2bcbb3cbc7bd644e595a035fc83</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Jin, Liang</creatorcontrib><creatorcontrib>Guo, Shaonan</creatorcontrib><creatorcontrib>Su, Haozhan</creatorcontrib><creatorcontrib>Song, Juheng</creatorcontrib><creatorcontrib>Jia, Yufang</creatorcontrib><collection>CrossRef</collection><jtitle>Journal of computational design and engineering</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Jin, Liang</au><au>Guo, Shaonan</au><au>Su, Haozhan</au><au>Song, Juheng</au><au>Jia, Yufang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A conditional adversarial operator network prediction method for current fields in armature-rail contact surface</atitle><jtitle>Journal of computational design and engineering</jtitle><date>2024-10-17</date><risdate>2024</risdate><volume>11</volume><issue>5</issue><spage>284</spage><epage>302</epage><pages>284-302</pages><issn>2288-5048</issn><eissn>2288-5048</eissn><abstract>Linear propulsion electromagnetic energy equipment can convert electromagnetic energy to kinetic energy instantaneously and has many advantages, such as high kinetic energy, efficiency, precision, and strong controllability. It surpasses traditional mechanical and chemical energy methods, significantly impacting various fields. Aiming at the numerical simulation method, which has problems with large computation volume and a long time of physical field simulation, the current field prediction method of linear propulsion electromagnetic energy equipment based on a Deep Generation Adversarial Operator Network is proposed. Firstly, deep operator network is combined with conditional generative adversarial network to obtain the knowledge-embedded conditional adversarial operator network (CGAONet) model. Then, Res-Transformer-Unet (RTUnet) is used as a branch network of CGAONet to establish the RTUnet-CGAONet model, and the current field method using a deep adversarial operator network is proposed. Finally, the finite element simulation model of the US public linear propulsion electromagnetic energy equipment calculation example is established to construct the simulation dataset from 1D excitation current value and time data to a 2D current field. The trained RTUnet-CGAONet model predicts the mean absolute percentage error of 2.94% in the 2D current field, and the model is minimally affected by the number of samples in the dataset. The results of this paper can achieve the second-level calculation of the current field under different excitation currents, which provides a new way of thinking for the analysis of dynamic characteristics of linear propulsion electromagnetic energy equipment.</abstract><doi>10.1093/jcde/qwae082</doi><tpages>19</tpages><orcidid>https://orcid.org/0009-0008-7257-7286</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2288-5048
ispartof Journal of computational design and engineering, 2024-10, Vol.11 (5), p.284-302
issn 2288-5048
2288-5048
language eng
recordid cdi_crossref_primary_10_1093_jcde_qwae082
source Oxford Journals Open Access Collection
title A conditional adversarial operator network prediction method for current fields in armature-rail contact surface
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T01%3A38%3A37IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-crossref&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20conditional%20adversarial%20operator%20network%20prediction%20method%20for%20current%20fields%20in%20armature-rail%20contact%20surface&rft.jtitle=Journal%20of%20computational%20design%20and%20engineering&rft.au=Jin,%20Liang&rft.date=2024-10-17&rft.volume=11&rft.issue=5&rft.spage=284&rft.epage=302&rft.pages=284-302&rft.issn=2288-5048&rft.eissn=2288-5048&rft_id=info:doi/10.1093/jcde/qwae082&rft_dat=%3Ccrossref%3E10_1093_jcde_qwae082%3C/crossref%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c160t-3f58642124be30c405bf5e27bd221d6454367e2bcbb3cbc7bd644e595a035fc83%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true