Fast Topology Optimization for PM Motors Using Variational Autoencoder and Neural Networks with Dropout
This study proposes a novel topology optimization (TO) method for permanent magnet (PM) motors based on a variational autoencoder (VAE) and a neural network (NN). The VAE is trained to embed various shapes generated from the TO into the latent space. The NN is trained to predict the characteristics...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on magnetics 2023-05, Vol.59 (5), p.1-1 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1 |
|---|---|
| container_issue | 5 |
| container_start_page | 1 |
| container_title | IEEE transactions on magnetics |
| container_volume | 59 |
| creator | Sato, Hayaho Igarashi, Hajime |
| description | This study proposes a novel topology optimization (TO) method for permanent magnet (PM) motors based on a variational autoencoder (VAE) and a neural network (NN). The VAE is trained to embed various shapes generated from the TO into the latent space. The NN is trained to predict the characteristics of the PM motor from its latent representation derived using the VAE. After training, TO is performed in the latent space based on the prediction using the NN. We adopt the Monte Carlo dropout to maintain prediction reliability using the NN during optimization, where prediction deviation is evaluated and used to eliminate unreliable solutions. The proposed method yields Pareto solutions within 80 s in a single-thread CPU machine, which is considerably faster than numerical analysis-based optimization, such as finite element analysis. |
| doi_str_mv | 10.1109/TMAG.2023.3242288 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_crossref_primary_10_1109_TMAG_2023_3242288</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10036443</ieee_id><sourcerecordid>2806217198</sourcerecordid><originalsourceid>FETCH-LOGICAL-c337t-3d670d50966e1b527baae41cdd873d7247337c880156f8ac0397570937efe7b3</originalsourceid><addsrcrecordid>eNpNkE1PAjEQhhujiYj-ABMPTTwv9mv7cSQqaMKHh9VrU3a7WIQttt0Q_PUuwsHTZGaedzJ5ALjFaIAxUg_FdDgeEETogBJGiJRnoIcVwxlCXJ2DHkJYZopxdgmuYlx1Lcsx6oHlyMQEC7_1a7_cw_k2uY37Mcn5BtY-wLcpnPrkQ4Tv0TVL-GGC-9uaNRy2ydum9JUN0DQVnNk2dOOZTTsfviLcufQJn0J3u03X4KI262hvTrUPitFz8fiSTebj18fhJCspFSmjFReoypHi3OJFTsTCGMtwWVVS0EoQJjqslBLhnNfSlIgqkQukqLC1FQvaB_fHs9vgv1sbk175NnTPRk0k4gQLrGRH4SNVBh9jsLXeBrcxYa8x0ged-qBTH3Tqk84uc3fMOGvtPx5Rzhilv5JKcWI</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2806217198</pqid></control><display><type>article</type><title>Fast Topology Optimization for PM Motors Using Variational Autoencoder and Neural Networks with Dropout</title><source>IEEE Electronic Library (IEL)</source><creator>Sato, Hayaho ; Igarashi, Hajime</creator><creatorcontrib>Sato, Hayaho ; Igarashi, Hajime</creatorcontrib><description>This study proposes a novel topology optimization (TO) method for permanent magnet (PM) motors based on a variational autoencoder (VAE) and a neural network (NN). The VAE is trained to embed various shapes generated from the TO into the latent space. The NN is trained to predict the characteristics of the PM motor from its latent representation derived using the VAE. After training, TO is performed in the latent space based on the prediction using the NN. We adopt the Monte Carlo dropout to maintain prediction reliability using the NN during optimization, where prediction deviation is evaluated and used to eliminate unreliable solutions. The proposed method yields Pareto solutions within 80 s in a single-thread CPU machine, which is considerably faster than numerical analysis-based optimization, such as finite element analysis.</description><identifier>ISSN: 0018-9464</identifier><identifier>EISSN: 1941-0069</identifier><identifier>DOI: 10.1109/TMAG.2023.3242288</identifier><identifier>CODEN: IEMGAQ</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Design optimization ; Finite element method ; Magnetism ; Motors ; Network topologies ; Neural networks ; Numerical analysis ; permanent magnet (PM) motors ; Permanent magnets ; Topology optimization</subject><ispartof>IEEE transactions on magnetics, 2023-05, Vol.59 (5), p.1-1</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c337t-3d670d50966e1b527baae41cdd873d7247337c880156f8ac0397570937efe7b3</citedby><cites>FETCH-LOGICAL-c337t-3d670d50966e1b527baae41cdd873d7247337c880156f8ac0397570937efe7b3</cites><orcidid>0000-0003-4330-236X ; 0000-0002-0852-3231</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10036443$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10036443$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Sato, Hayaho</creatorcontrib><creatorcontrib>Igarashi, Hajime</creatorcontrib><title>Fast Topology Optimization for PM Motors Using Variational Autoencoder and Neural Networks with Dropout</title><title>IEEE transactions on magnetics</title><addtitle>TMAG</addtitle><description>This study proposes a novel topology optimization (TO) method for permanent magnet (PM) motors based on a variational autoencoder (VAE) and a neural network (NN). The VAE is trained to embed various shapes generated from the TO into the latent space. The NN is trained to predict the characteristics of the PM motor from its latent representation derived using the VAE. After training, TO is performed in the latent space based on the prediction using the NN. We adopt the Monte Carlo dropout to maintain prediction reliability using the NN during optimization, where prediction deviation is evaluated and used to eliminate unreliable solutions. The proposed method yields Pareto solutions within 80 s in a single-thread CPU machine, which is considerably faster than numerical analysis-based optimization, such as finite element analysis.</description><subject>Design optimization</subject><subject>Finite element method</subject><subject>Magnetism</subject><subject>Motors</subject><subject>Network topologies</subject><subject>Neural networks</subject><subject>Numerical analysis</subject><subject>permanent magnet (PM) motors</subject><subject>Permanent magnets</subject><subject>Topology optimization</subject><issn>0018-9464</issn><issn>1941-0069</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpNkE1PAjEQhhujiYj-ABMPTTwv9mv7cSQqaMKHh9VrU3a7WIQttt0Q_PUuwsHTZGaedzJ5ALjFaIAxUg_FdDgeEETogBJGiJRnoIcVwxlCXJ2DHkJYZopxdgmuYlx1Lcsx6oHlyMQEC7_1a7_cw_k2uY37Mcn5BtY-wLcpnPrkQ4Tv0TVL-GGC-9uaNRy2ydum9JUN0DQVnNk2dOOZTTsfviLcufQJn0J3u03X4KI262hvTrUPitFz8fiSTebj18fhJCspFSmjFReoypHi3OJFTsTCGMtwWVVS0EoQJjqslBLhnNfSlIgqkQukqLC1FQvaB_fHs9vgv1sbk175NnTPRk0k4gQLrGRH4SNVBh9jsLXeBrcxYa8x0ged-qBTH3Tqk84uc3fMOGvtPx5Rzhilv5JKcWI</recordid><startdate>20230501</startdate><enddate>20230501</enddate><creator>Sato, Hayaho</creator><creator>Igarashi, Hajime</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>7U5</scope><scope>8BQ</scope><scope>8FD</scope><scope>JG9</scope><scope>L7M</scope><orcidid>https://orcid.org/0000-0003-4330-236X</orcidid><orcidid>https://orcid.org/0000-0002-0852-3231</orcidid></search><sort><creationdate>20230501</creationdate><title>Fast Topology Optimization for PM Motors Using Variational Autoencoder and Neural Networks with Dropout</title><author>Sato, Hayaho ; Igarashi, Hajime</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c337t-3d670d50966e1b527baae41cdd873d7247337c880156f8ac0397570937efe7b3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Design optimization</topic><topic>Finite element method</topic><topic>Magnetism</topic><topic>Motors</topic><topic>Network topologies</topic><topic>Neural networks</topic><topic>Numerical analysis</topic><topic>permanent magnet (PM) motors</topic><topic>Permanent magnets</topic><topic>Topology optimization</topic><toplevel>online_resources</toplevel><creatorcontrib>Sato, Hayaho</creatorcontrib><creatorcontrib>Igarashi, Hajime</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Electronics & Communications Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>Materials Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>IEEE transactions on magnetics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Sato, Hayaho</au><au>Igarashi, Hajime</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Fast Topology Optimization for PM Motors Using Variational Autoencoder and Neural Networks with Dropout</atitle><jtitle>IEEE transactions on magnetics</jtitle><stitle>TMAG</stitle><date>2023-05-01</date><risdate>2023</risdate><volume>59</volume><issue>5</issue><spage>1</spage><epage>1</epage><pages>1-1</pages><issn>0018-9464</issn><eissn>1941-0069</eissn><coden>IEMGAQ</coden><abstract>This study proposes a novel topology optimization (TO) method for permanent magnet (PM) motors based on a variational autoencoder (VAE) and a neural network (NN). The VAE is trained to embed various shapes generated from the TO into the latent space. The NN is trained to predict the characteristics of the PM motor from its latent representation derived using the VAE. After training, TO is performed in the latent space based on the prediction using the NN. We adopt the Monte Carlo dropout to maintain prediction reliability using the NN during optimization, where prediction deviation is evaluated and used to eliminate unreliable solutions. The proposed method yields Pareto solutions within 80 s in a single-thread CPU machine, which is considerably faster than numerical analysis-based optimization, such as finite element analysis.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TMAG.2023.3242288</doi><tpages>1</tpages><orcidid>https://orcid.org/0000-0003-4330-236X</orcidid><orcidid>https://orcid.org/0000-0002-0852-3231</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 0018-9464 |
| ispartof | IEEE transactions on magnetics, 2023-05, Vol.59 (5), p.1-1 |
| issn | 0018-9464 1941-0069 |
| language | eng |
| recordid | cdi_crossref_primary_10_1109_TMAG_2023_3242288 |
| source | IEEE Electronic Library (IEL) |
| subjects | Design optimization Finite element method Magnetism Motors Network topologies Neural networks Numerical analysis permanent magnet (PM) motors Permanent magnets Topology optimization |
| title | Fast Topology Optimization for PM Motors Using Variational Autoencoder and Neural Networks with Dropout |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-19T14%3A45%3A21IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Fast%20Topology%20Optimization%20for%20PM%20Motors%20Using%20Variational%20Autoencoder%20and%20Neural%20Networks%20with%20Dropout&rft.jtitle=IEEE%20transactions%20on%20magnetics&rft.au=Sato,%20Hayaho&rft.date=2023-05-01&rft.volume=59&rft.issue=5&rft.spage=1&rft.epage=1&rft.pages=1-1&rft.issn=0018-9464&rft.eissn=1941-0069&rft.coden=IEMGAQ&rft_id=info:doi/10.1109/TMAG.2023.3242288&rft_dat=%3Cproquest_RIE%3E2806217198%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2806217198&rft_id=info:pmid/&rft_ieee_id=10036443&rfr_iscdi=true |