Surfel convolutional neural network for support detection in additive manufacturing
Support generation is one of the crucial steps in 3D printing to make sure the overhang structures can be fabricated. The first step of support generation is to detect which regions need support structures. Normal-based methods can determine the support regions fast but find many unnecessary locatio...
Gespeichert in:
Veröffentlicht in: | International journal of advanced manufacturing technology 2019-12, Vol.105 (9), p.3593-3604 |
---|---|
Hauptverfasser: | , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 3604 |
---|---|
container_issue | 9 |
container_start_page | 3593 |
container_title | International journal of advanced manufacturing technology |
container_volume | 105 |
creator | Huang, Jida Kwok, Tsz-Ho Zhou, Chi Xu, Wenyao |
description | Support generation is one of the crucial steps in 3D printing to make sure the overhang structures can be fabricated. The first step of support generation is to detect which regions need support structures. Normal-based methods can determine the support regions fast but find many unnecessary locations which could be potentially self-supported. Image-based methods conduct a layer-by-layer comparison to find support regions, which could make use of material self-support capability; however, it sacrifices the computational cost and may still fail in some applications due to the loss of topology information when conducting offset and boolean operations based on the image. In order to overcome the difficulties of image-based methods, this paper proposes a surfel convolutional neural network (SCNN)-based approach for support detection. In this method, the sampling point on the surface with normal information, named
surfel
(
surf
ace
el
ement), is defined through layered depth-normal image (LDNI) sampling method. A local surfel image which represents the local topology information of the sampling point in the solid model is then constructed. A set of models with ground-truth support regions is used to train the deep neural network. Experimental results show that the proposed method outperforms the normal-based method and image-based method in terms of accuracy, reliability, and computational cost. |
doi_str_mv | 10.1007/s00170-019-03792-1 |
format | Article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2490851354</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2490851354</sourcerecordid><originalsourceid>FETCH-LOGICAL-c439t-c2678f01e25b4d28f60f574423a23e43e64ab7e99eb0a26d954756712c022ebe3</originalsourceid><addsrcrecordid>eNp9kDtPwzAUhS0EEqXwB5gsMRuuH_FjRBUvqRJDYbacxEYpbRzspIh_T9ogsXU6y3eO7v0QuqZwSwHUXQagCghQQ4Arwwg9QTMqOCccaHGKZsCkJlxJfY4ucl6PuKRSz9BqNaTgN7iK7S5uhr6Jrdvg1g_pEP13TJ84xITz0HUx9bj2va_2GG5a7Oq66Zudx1vXDsFV_ZCa9uMSnQW3yf7qL-fo_fHhbfFMlq9PL4v7JakENz2pmFQ6APWsKEXNdJAQCiUE445xL7iXwpXKG-NLcEzWphCqkIqyChjzpedzdDPtdil-DT73dh2HNN6fLRMGdEF5IY5SnIHWwkg9UmyiqhRzTj7YLjVbl34sBbtXbCfFdlRsD4otHUt8KuVu_7dP_9NHWr_jmX5z</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2320884968</pqid></control><display><type>article</type><title>Surfel convolutional neural network for support detection in additive manufacturing</title><source>SpringerLink_现刊</source><creator>Huang, Jida ; Kwok, Tsz-Ho ; Zhou, Chi ; Xu, Wenyao</creator><creatorcontrib>Huang, Jida ; Kwok, Tsz-Ho ; Zhou, Chi ; Xu, Wenyao</creatorcontrib><description>Support generation is one of the crucial steps in 3D printing to make sure the overhang structures can be fabricated. The first step of support generation is to detect which regions need support structures. Normal-based methods can determine the support regions fast but find many unnecessary locations which could be potentially self-supported. Image-based methods conduct a layer-by-layer comparison to find support regions, which could make use of material self-support capability; however, it sacrifices the computational cost and may still fail in some applications due to the loss of topology information when conducting offset and boolean operations based on the image. In order to overcome the difficulties of image-based methods, this paper proposes a surfel convolutional neural network (SCNN)-based approach for support detection. In this method, the sampling point on the surface with normal information, named
surfel
(
surf
ace
el
ement), is defined through layered depth-normal image (LDNI) sampling method. A local surfel image which represents the local topology information of the sampling point in the solid model is then constructed. A set of models with ground-truth support regions is used to train the deep neural network. Experimental results show that the proposed method outperforms the normal-based method and image-based method in terms of accuracy, reliability, and computational cost.</description><identifier>ISSN: 0268-3768</identifier><identifier>EISSN: 1433-3015</identifier><identifier>DOI: 10.1007/s00170-019-03792-1</identifier><language>eng</language><publisher>London: Springer London</publisher><subject>Artificial neural networks ; Boolean algebra ; CAE) and Design ; Computational efficiency ; Computer-Aided Engineering (CAD ; Computing costs ; Engineering ; Industrial and Production Engineering ; Mechanical Engineering ; Media Management ; Methods ; Neural networks ; Original Article ; Sampling ; Sampling methods ; Three dimensional printing ; Topology</subject><ispartof>International journal of advanced manufacturing technology, 2019-12, Vol.105 (9), p.3593-3604</ispartof><rights>Springer-Verlag London Ltd., part of Springer Nature 2019</rights><rights>The International Journal of Advanced Manufacturing Technology is a copyright of Springer, (2019). All Rights Reserved.</rights><rights>Springer-Verlag London Ltd., part of Springer Nature 2019.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c439t-c2678f01e25b4d28f60f574423a23e43e64ab7e99eb0a26d954756712c022ebe3</citedby><cites>FETCH-LOGICAL-c439t-c2678f01e25b4d28f60f574423a23e43e64ab7e99eb0a26d954756712c022ebe3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s00170-019-03792-1$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s00170-019-03792-1$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,41488,42557,51319</link.rule.ids></links><search><creatorcontrib>Huang, Jida</creatorcontrib><creatorcontrib>Kwok, Tsz-Ho</creatorcontrib><creatorcontrib>Zhou, Chi</creatorcontrib><creatorcontrib>Xu, Wenyao</creatorcontrib><title>Surfel convolutional neural network for support detection in additive manufacturing</title><title>International journal of advanced manufacturing technology</title><addtitle>Int J Adv Manuf Technol</addtitle><description>Support generation is one of the crucial steps in 3D printing to make sure the overhang structures can be fabricated. The first step of support generation is to detect which regions need support structures. Normal-based methods can determine the support regions fast but find many unnecessary locations which could be potentially self-supported. Image-based methods conduct a layer-by-layer comparison to find support regions, which could make use of material self-support capability; however, it sacrifices the computational cost and may still fail in some applications due to the loss of topology information when conducting offset and boolean operations based on the image. In order to overcome the difficulties of image-based methods, this paper proposes a surfel convolutional neural network (SCNN)-based approach for support detection. In this method, the sampling point on the surface with normal information, named
surfel
(
surf
ace
el
ement), is defined through layered depth-normal image (LDNI) sampling method. A local surfel image which represents the local topology information of the sampling point in the solid model is then constructed. A set of models with ground-truth support regions is used to train the deep neural network. Experimental results show that the proposed method outperforms the normal-based method and image-based method in terms of accuracy, reliability, and computational cost.</description><subject>Artificial neural networks</subject><subject>Boolean algebra</subject><subject>CAE) and Design</subject><subject>Computational efficiency</subject><subject>Computer-Aided Engineering (CAD</subject><subject>Computing costs</subject><subject>Engineering</subject><subject>Industrial and Production Engineering</subject><subject>Mechanical Engineering</subject><subject>Media Management</subject><subject>Methods</subject><subject>Neural networks</subject><subject>Original Article</subject><subject>Sampling</subject><subject>Sampling methods</subject><subject>Three dimensional printing</subject><subject>Topology</subject><issn>0268-3768</issn><issn>1433-3015</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>AFKRA</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNp9kDtPwzAUhS0EEqXwB5gsMRuuH_FjRBUvqRJDYbacxEYpbRzspIh_T9ogsXU6y3eO7v0QuqZwSwHUXQagCghQQ4Arwwg9QTMqOCccaHGKZsCkJlxJfY4ucl6PuKRSz9BqNaTgN7iK7S5uhr6Jrdvg1g_pEP13TJ84xITz0HUx9bj2va_2GG5a7Oq66Zudx1vXDsFV_ZCa9uMSnQW3yf7qL-fo_fHhbfFMlq9PL4v7JakENz2pmFQ6APWsKEXNdJAQCiUE445xL7iXwpXKG-NLcEzWphCqkIqyChjzpedzdDPtdil-DT73dh2HNN6fLRMGdEF5IY5SnIHWwkg9UmyiqhRzTj7YLjVbl34sBbtXbCfFdlRsD4otHUt8KuVu_7dP_9NHWr_jmX5z</recordid><startdate>20191201</startdate><enddate>20191201</enddate><creator>Huang, Jida</creator><creator>Kwok, Tsz-Ho</creator><creator>Zhou, Chi</creator><creator>Xu, Wenyao</creator><general>Springer London</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>AFKRA</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20191201</creationdate><title>Surfel convolutional neural network for support detection in additive manufacturing</title><author>Huang, Jida ; Kwok, Tsz-Ho ; Zhou, Chi ; Xu, Wenyao</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c439t-c2678f01e25b4d28f60f574423a23e43e64ab7e99eb0a26d954756712c022ebe3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Artificial neural networks</topic><topic>Boolean algebra</topic><topic>CAE) and Design</topic><topic>Computational efficiency</topic><topic>Computer-Aided Engineering (CAD</topic><topic>Computing costs</topic><topic>Engineering</topic><topic>Industrial and Production Engineering</topic><topic>Mechanical Engineering</topic><topic>Media Management</topic><topic>Methods</topic><topic>Neural networks</topic><topic>Original Article</topic><topic>Sampling</topic><topic>Sampling methods</topic><topic>Three dimensional printing</topic><topic>Topology</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Huang, Jida</creatorcontrib><creatorcontrib>Kwok, Tsz-Ho</creatorcontrib><creatorcontrib>Zhou, Chi</creatorcontrib><creatorcontrib>Xu, Wenyao</creatorcontrib><collection>CrossRef</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering 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><jtitle>International journal of advanced manufacturing technology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Huang, Jida</au><au>Kwok, Tsz-Ho</au><au>Zhou, Chi</au><au>Xu, Wenyao</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Surfel convolutional neural network for support detection in additive manufacturing</atitle><jtitle>International journal of advanced manufacturing technology</jtitle><stitle>Int J Adv Manuf Technol</stitle><date>2019-12-01</date><risdate>2019</risdate><volume>105</volume><issue>9</issue><spage>3593</spage><epage>3604</epage><pages>3593-3604</pages><issn>0268-3768</issn><eissn>1433-3015</eissn><abstract>Support generation is one of the crucial steps in 3D printing to make sure the overhang structures can be fabricated. The first step of support generation is to detect which regions need support structures. Normal-based methods can determine the support regions fast but find many unnecessary locations which could be potentially self-supported. Image-based methods conduct a layer-by-layer comparison to find support regions, which could make use of material self-support capability; however, it sacrifices the computational cost and may still fail in some applications due to the loss of topology information when conducting offset and boolean operations based on the image. In order to overcome the difficulties of image-based methods, this paper proposes a surfel convolutional neural network (SCNN)-based approach for support detection. In this method, the sampling point on the surface with normal information, named
surfel
(
surf
ace
el
ement), is defined through layered depth-normal image (LDNI) sampling method. A local surfel image which represents the local topology information of the sampling point in the solid model is then constructed. A set of models with ground-truth support regions is used to train the deep neural network. Experimental results show that the proposed method outperforms the normal-based method and image-based method in terms of accuracy, reliability, and computational cost.</abstract><cop>London</cop><pub>Springer London</pub><doi>10.1007/s00170-019-03792-1</doi><tpages>12</tpages><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0268-3768 |
ispartof | International journal of advanced manufacturing technology, 2019-12, Vol.105 (9), p.3593-3604 |
issn | 0268-3768 1433-3015 |
language | eng |
recordid | cdi_proquest_journals_2490851354 |
source | SpringerLink_现刊 |
subjects | Artificial neural networks Boolean algebra CAE) and Design Computational efficiency Computer-Aided Engineering (CAD Computing costs Engineering Industrial and Production Engineering Mechanical Engineering Media Management Methods Neural networks Original Article Sampling Sampling methods Three dimensional printing Topology |
title | Surfel convolutional neural network for support detection in additive manufacturing |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T10%3A24%3A40IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Surfel%20convolutional%20neural%20network%20for%20support%20detection%20in%20additive%20manufacturing&rft.jtitle=International%20journal%20of%20advanced%20manufacturing%20technology&rft.au=Huang,%20Jida&rft.date=2019-12-01&rft.volume=105&rft.issue=9&rft.spage=3593&rft.epage=3604&rft.pages=3593-3604&rft.issn=0268-3768&rft.eissn=1433-3015&rft_id=info:doi/10.1007/s00170-019-03792-1&rft_dat=%3Cproquest_cross%3E2490851354%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2320884968&rft_id=info:pmid/&rfr_iscdi=true |