Data-Driven, Parameterized Reduced-order Models for Predicting Distortion in Metal 3D Printing
In Laser Powder Bed Fusion (LPBF), the applied laser energy produces high thermal gradients that lead to unacceptable final part distortion. Accurate distortion prediction is essential for optimizing the 3D printing process and manufacturing a part that meets geometric accuracy requirements. This st...
Gespeichert in:
| Veröffentlicht in: | arXiv.org 2024-12 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | arXiv.org |
| container_volume | |
| creator | Deo, Indu Kant Choi, Youngsoo Khairallah, Saad A Reikher, Alexandre Strantza, Maria |
| description | In Laser Powder Bed Fusion (LPBF), the applied laser energy produces high thermal gradients that lead to unacceptable final part distortion. Accurate distortion prediction is essential for optimizing the 3D printing process and manufacturing a part that meets geometric accuracy requirements. This study introduces data-driven parameterized reduced-order models (ROMs) to predict distortion in LPBF across various machine process settings. We propose a ROM framework that combines Proper Orthogonal Decomposition (POD) with Gaussian Process Regression (GPR) and compare its performance against a deep-learning based parameterized graph convolutional autoencoder (GCA). The POD-GPR model demonstrates high accuracy, predicting distortions within \(\pm0.001mm\), and delivers a computational speed-up of approximately 1800x. |
| format | Article |
| fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3142375913</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3142375913</sourcerecordid><originalsourceid>FETCH-proquest_journals_31423759133</originalsourceid><addsrcrecordid>eNqNyrEKwjAUQNEgCBbtPzxwNdAmrdXZKi4FEWdLaF4lpSb6kjr49VbwA5zucO6ERULKlG8yIWYs9r5LkkSsC5HnMmLXUgXFSzIvtCs4KVJ3DEjmjRrOqIcGNXekkaByGnsPrSM4EWrTBGNvUBofHAXjLBgLFQbVgyzHw9ivL9i0Vb3H-Nc5Wx72l92RP8g9B_Sh7txAdqRappmQRb5Npfzv-gD4LENr</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3142375913</pqid></control><display><type>article</type><title>Data-Driven, Parameterized Reduced-order Models for Predicting Distortion in Metal 3D Printing</title><source>Free E- Journals</source><creator>Deo, Indu Kant ; Choi, Youngsoo ; Khairallah, Saad A ; Reikher, Alexandre ; Strantza, Maria</creator><creatorcontrib>Deo, Indu Kant ; Choi, Youngsoo ; Khairallah, Saad A ; Reikher, Alexandre ; Strantza, Maria</creatorcontrib><description>In Laser Powder Bed Fusion (LPBF), the applied laser energy produces high thermal gradients that lead to unacceptable final part distortion. Accurate distortion prediction is essential for optimizing the 3D printing process and manufacturing a part that meets geometric accuracy requirements. This study introduces data-driven parameterized reduced-order models (ROMs) to predict distortion in LPBF across various machine process settings. We propose a ROM framework that combines Proper Orthogonal Decomposition (POD) with Gaussian Process Regression (GPR) and compare its performance against a deep-learning based parameterized graph convolutional autoencoder (GCA). The POD-GPR model demonstrates high accuracy, predicting distortions within \(\pm0.001mm\), and delivers a computational speed-up of approximately 1800x.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Distortion ; Gaussian process ; Geometric accuracy ; Parameterization ; Powder beds ; Predictions ; Proper Orthogonal Decomposition ; Reduced order models ; Three dimensional printing</subject><ispartof>arXiv.org, 2024-12</ispartof><rights>2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>776,780</link.rule.ids></links><search><creatorcontrib>Deo, Indu Kant</creatorcontrib><creatorcontrib>Choi, Youngsoo</creatorcontrib><creatorcontrib>Khairallah, Saad A</creatorcontrib><creatorcontrib>Reikher, Alexandre</creatorcontrib><creatorcontrib>Strantza, Maria</creatorcontrib><title>Data-Driven, Parameterized Reduced-order Models for Predicting Distortion in Metal 3D Printing</title><title>arXiv.org</title><description>In Laser Powder Bed Fusion (LPBF), the applied laser energy produces high thermal gradients that lead to unacceptable final part distortion. Accurate distortion prediction is essential for optimizing the 3D printing process and manufacturing a part that meets geometric accuracy requirements. This study introduces data-driven parameterized reduced-order models (ROMs) to predict distortion in LPBF across various machine process settings. We propose a ROM framework that combines Proper Orthogonal Decomposition (POD) with Gaussian Process Regression (GPR) and compare its performance against a deep-learning based parameterized graph convolutional autoencoder (GCA). The POD-GPR model demonstrates high accuracy, predicting distortions within \(\pm0.001mm\), and delivers a computational speed-up of approximately 1800x.</description><subject>Distortion</subject><subject>Gaussian process</subject><subject>Geometric accuracy</subject><subject>Parameterization</subject><subject>Powder beds</subject><subject>Predictions</subject><subject>Proper Orthogonal Decomposition</subject><subject>Reduced order models</subject><subject>Three dimensional printing</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNyrEKwjAUQNEgCBbtPzxwNdAmrdXZKi4FEWdLaF4lpSb6kjr49VbwA5zucO6ERULKlG8yIWYs9r5LkkSsC5HnMmLXUgXFSzIvtCs4KVJ3DEjmjRrOqIcGNXekkaByGnsPrSM4EWrTBGNvUBofHAXjLBgLFQbVgyzHw9ivL9i0Vb3H-Nc5Wx72l92RP8g9B_Sh7txAdqRappmQRb5Npfzv-gD4LENr</recordid><startdate>20241205</startdate><enddate>20241205</enddate><creator>Deo, Indu Kant</creator><creator>Choi, Youngsoo</creator><creator>Khairallah, Saad A</creator><creator>Reikher, Alexandre</creator><creator>Strantza, Maria</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20241205</creationdate><title>Data-Driven, Parameterized Reduced-order Models for Predicting Distortion in Metal 3D Printing</title><author>Deo, Indu Kant ; Choi, Youngsoo ; Khairallah, Saad A ; Reikher, Alexandre ; Strantza, Maria</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_31423759133</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Distortion</topic><topic>Gaussian process</topic><topic>Geometric accuracy</topic><topic>Parameterization</topic><topic>Powder beds</topic><topic>Predictions</topic><topic>Proper Orthogonal Decomposition</topic><topic>Reduced order models</topic><topic>Three dimensional printing</topic><toplevel>online_resources</toplevel><creatorcontrib>Deo, Indu Kant</creatorcontrib><creatorcontrib>Choi, Youngsoo</creatorcontrib><creatorcontrib>Khairallah, Saad A</creatorcontrib><creatorcontrib>Reikher, Alexandre</creatorcontrib><creatorcontrib>Strantza, Maria</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection (ProQuest)</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Deo, Indu Kant</au><au>Choi, Youngsoo</au><au>Khairallah, Saad A</au><au>Reikher, Alexandre</au><au>Strantza, Maria</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Data-Driven, Parameterized Reduced-order Models for Predicting Distortion in Metal 3D Printing</atitle><jtitle>arXiv.org</jtitle><date>2024-12-05</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>In Laser Powder Bed Fusion (LPBF), the applied laser energy produces high thermal gradients that lead to unacceptable final part distortion. Accurate distortion prediction is essential for optimizing the 3D printing process and manufacturing a part that meets geometric accuracy requirements. This study introduces data-driven parameterized reduced-order models (ROMs) to predict distortion in LPBF across various machine process settings. We propose a ROM framework that combines Proper Orthogonal Decomposition (POD) with Gaussian Process Regression (GPR) and compare its performance against a deep-learning based parameterized graph convolutional autoencoder (GCA). The POD-GPR model demonstrates high accuracy, predicting distortions within \(\pm0.001mm\), and delivers a computational speed-up of approximately 1800x.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | EISSN: 2331-8422 |
| ispartof | arXiv.org, 2024-12 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_proquest_journals_3142375913 |
| source | Free E- Journals |
| subjects | Distortion Gaussian process Geometric accuracy Parameterization Powder beds Predictions Proper Orthogonal Decomposition Reduced order models Three dimensional printing |
| title | Data-Driven, Parameterized Reduced-order Models for Predicting Distortion in Metal 3D Printing |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-24T12%3A19%3A54IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Data-Driven,%20Parameterized%20Reduced-order%20Models%20for%20Predicting%20Distortion%20in%20Metal%203D%20Printing&rft.jtitle=arXiv.org&rft.au=Deo,%20Indu%20Kant&rft.date=2024-12-05&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3142375913%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3142375913&rft_id=info:pmid/&rfr_iscdi=true |