METHOD AND SYSTEM FOR DESIGNING ELECTRICAL MACHINES USING REINFORCEMENT LEARNING

An example method of designing an electrical machine includes providing at least one goal and at least one design constraint for a desired electrical machine to a deep neural network that comprises a plurality of nodes representing a plurality of prior electrical machine designs, the plurality of no...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wawrzyniak, Beata I, Kshirsagar, Parag M, Venugopalan, Vivek
Format: Patent
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Wawrzyniak, Beata I
Kshirsagar, Parag M
Venugopalan, Vivek
description An example method of designing an electrical machine includes providing at least one goal and at least one design constraint for a desired electrical machine to a deep neural network that comprises a plurality of nodes representing a plurality of prior electrical machine designs, the plurality of nodes connected by weights, each weight representing a correlation strength between two nodes. A proposed design is generated from the deep neural network for an electrical machine based on the goal(s) and design constraint(s). A plurality of the weights are adjusted based on a reward that rates at least one aspect of the proposed design. The proposed design is modified using the deep neural network after the weight adjustment. The adjusting and modifying are iteratively repeated to generate subsequent iterations of the proposed design, each subsequent iteration based on the reward from a preceding iteration. A system for designing electrical machines is also disclosed.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2019332725A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2019332725A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2019332725A13</originalsourceid><addsrcrecordid>eNqNi7EKwjAUALM4iPoPD5wFmyDSMSSvTSB5lbx0cCpF4iRaqP-PFvwApxvubi0uEbPrLGiywFfOGKHpElhk35KnFjCgyckbHSBq4zwhQ8-LSejp2xqMSBkC6rQMW7G6j4-57H7ciH2D2bhDmV5DmafxVp7lPfQsj1WtlDzLk67Uf9UHMVgwDg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>METHOD AND SYSTEM FOR DESIGNING ELECTRICAL MACHINES USING REINFORCEMENT LEARNING</title><source>esp@cenet</source><creator>Wawrzyniak, Beata I ; Kshirsagar, Parag M ; Venugopalan, Vivek</creator><creatorcontrib>Wawrzyniak, Beata I ; Kshirsagar, Parag M ; Venugopalan, Vivek</creatorcontrib><description>An example method of designing an electrical machine includes providing at least one goal and at least one design constraint for a desired electrical machine to a deep neural network that comprises a plurality of nodes representing a plurality of prior electrical machine designs, the plurality of nodes connected by weights, each weight representing a correlation strength between two nodes. A proposed design is generated from the deep neural network for an electrical machine based on the goal(s) and design constraint(s). A plurality of the weights are adjusted based on a reward that rates at least one aspect of the proposed design. The proposed design is modified using the deep neural network after the weight adjustment. The adjusting and modifying are iteratively repeated to generate subsequent iterations of the proposed design, each subsequent iteration based on the reward from a preceding iteration. A system for designing electrical machines is also disclosed.</description><language>eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2019</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20191031&amp;DB=EPODOC&amp;CC=US&amp;NR=2019332725A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,309,781,886,25568,76551</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20191031&amp;DB=EPODOC&amp;CC=US&amp;NR=2019332725A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Wawrzyniak, Beata I</creatorcontrib><creatorcontrib>Kshirsagar, Parag M</creatorcontrib><creatorcontrib>Venugopalan, Vivek</creatorcontrib><title>METHOD AND SYSTEM FOR DESIGNING ELECTRICAL MACHINES USING REINFORCEMENT LEARNING</title><description>An example method of designing an electrical machine includes providing at least one goal and at least one design constraint for a desired electrical machine to a deep neural network that comprises a plurality of nodes representing a plurality of prior electrical machine designs, the plurality of nodes connected by weights, each weight representing a correlation strength between two nodes. A proposed design is generated from the deep neural network for an electrical machine based on the goal(s) and design constraint(s). A plurality of the weights are adjusted based on a reward that rates at least one aspect of the proposed design. The proposed design is modified using the deep neural network after the weight adjustment. The adjusting and modifying are iteratively repeated to generate subsequent iterations of the proposed design, each subsequent iteration based on the reward from a preceding iteration. A system for designing electrical machines is also disclosed.</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2019</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNi7EKwjAUALM4iPoPD5wFmyDSMSSvTSB5lbx0cCpF4iRaqP-PFvwApxvubi0uEbPrLGiywFfOGKHpElhk35KnFjCgyckbHSBq4zwhQ8-LSejp2xqMSBkC6rQMW7G6j4-57H7ciH2D2bhDmV5DmafxVp7lPfQsj1WtlDzLk67Uf9UHMVgwDg</recordid><startdate>20191031</startdate><enddate>20191031</enddate><creator>Wawrzyniak, Beata I</creator><creator>Kshirsagar, Parag M</creator><creator>Venugopalan, Vivek</creator><scope>EVB</scope></search><sort><creationdate>20191031</creationdate><title>METHOD AND SYSTEM FOR DESIGNING ELECTRICAL MACHINES USING REINFORCEMENT LEARNING</title><author>Wawrzyniak, Beata I ; Kshirsagar, Parag M ; Venugopalan, Vivek</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2019332725A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2019</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>Wawrzyniak, Beata I</creatorcontrib><creatorcontrib>Kshirsagar, Parag M</creatorcontrib><creatorcontrib>Venugopalan, Vivek</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Wawrzyniak, Beata I</au><au>Kshirsagar, Parag M</au><au>Venugopalan, Vivek</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>METHOD AND SYSTEM FOR DESIGNING ELECTRICAL MACHINES USING REINFORCEMENT LEARNING</title><date>2019-10-31</date><risdate>2019</risdate><abstract>An example method of designing an electrical machine includes providing at least one goal and at least one design constraint for a desired electrical machine to a deep neural network that comprises a plurality of nodes representing a plurality of prior electrical machine designs, the plurality of nodes connected by weights, each weight representing a correlation strength between two nodes. A proposed design is generated from the deep neural network for an electrical machine based on the goal(s) and design constraint(s). A plurality of the weights are adjusted based on a reward that rates at least one aspect of the proposed design. The proposed design is modified using the deep neural network after the weight adjustment. The adjusting and modifying are iteratively repeated to generate subsequent iterations of the proposed design, each subsequent iteration based on the reward from a preceding iteration. A system for designing electrical machines is also disclosed.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_US2019332725A1
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title METHOD AND SYSTEM FOR DESIGNING ELECTRICAL MACHINES USING REINFORCEMENT LEARNING
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-17T07%3A06%3A34IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=Wawrzyniak,%20Beata%20I&rft.date=2019-10-31&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2019332725A1%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true