Residue buildup predictive modeling for stencil cleaning profile decision-making using recurrent neural network
•Enhance the stencil printing process performance by proper cleaning profile selection.•Residue buildup amount is a key criterion for stencil cleaning profile selection.•Image processing to quantify residue buildup amount on the stencil seating surface.•Recurrent neural network for accurate residue...
Gespeichert in:
Veröffentlicht in: | Robotics and computer-integrated manufacturing 2021-04, Vol.68, p.102041, Article 102041 |
---|---|
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 | 102041 |
container_title | Robotics and computer-integrated manufacturing |
container_volume | 68 |
creator | Alelaumi, Shrouq Khader, Nourma He, Jingxi Lam, Sarah Yoon, Sang Won |
description | •Enhance the stencil printing process performance by proper cleaning profile selection.•Residue buildup amount is a key criterion for stencil cleaning profile selection.•Image processing to quantify residue buildup amount on the stencil seating surface.•Recurrent neural network for accurate residue buildup prediction.
This research proposes a novel framework to control the stencil cleaning profile selection in the stencil printing process (SPP). The SPP is a major contributor to yield loss in surface mount technology (SMT). Enhancement in SPP performance is critical to improving the printed circuit board (PCB) assembly line. The selection of a solvent-based or a dry-based cleaning profile is challenging, but the choice determines the effectiveness and efficiency of the stencil cleaning operation. The amount of residue buildup under the stencil is the main criterion used to decide the appropriate cleaning profile in SPP. In this research, a multi-dimensional temporal recurrent neural network (RNN) approach is used to accurately predict the amount of residue buildup on the underneath surface of the stencil in real-time. Specifically, the long short-term memory (LSTM) architecture is trained using actual residue buildup data. The proposed LSTM prediction model is compared with other state-of-the-art regression models such as multilayer perceptron (MLP) and ensemble learning models. Experimental results show the proposed LSTM model outperforms the state-of-the-art regression models and accurately predicts the stencil status. The proposed research aids decision-makers in the SPP line to select the appropriate stencil cleaning profile adaptively and in real-time. As a result, the overall SPP performance is improved. |
doi_str_mv | 10.1016/j.rcim.2020.102041 |
format | Article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2486864790</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0736584520302520</els_id><sourcerecordid>2486864790</sourcerecordid><originalsourceid>FETCH-LOGICAL-c328t-dc4612a211136e019d56303715012424b660b8750d796e925991067f7c93bc493</originalsourceid><addsrcrecordid>eNp9kE1LxDAQhoMouK7-AU8Fz13z1aQBL7L4BQuC6Dm0yVTSbZuatCv-e1PWs5cZeJl35p0HoWuCNwQTcdtugnH9hmK6CBRzcoJWpJQqpwWTp2iFJRN5UfLiHF3E2GKMKS_YCvk3iM7OkNWz6-w8ZmMA68zkDpD13kLnhs-s8SGLEwzGdZnpoBoWcQy-cR1kFoyLzg95X-0XfY5LDWDmEGCYsgHmUHWpTd8-7C_RWVN1Ea7--hp9PD68b5_z3evTy_Z-lxtGyym3hgtCK0oIYQIwUbYQDDNJCkwop7wWAtelLLCVSoCihVIEC9lIo1htuGJrdHPcm2J-zRAn3fo5DOmkprwUpeBS4TRFj1Mm-BgDNHoMrq_CjyZYL2B1qxewegGrj2CT6e5ogpT_4CDoaFyCk7ilrydtvfvP_gtgF4GL</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2486864790</pqid></control><display><type>article</type><title>Residue buildup predictive modeling for stencil cleaning profile decision-making using recurrent neural network</title><source>Access via ScienceDirect (Elsevier)</source><creator>Alelaumi, Shrouq ; Khader, Nourma ; He, Jingxi ; Lam, Sarah ; Yoon, Sang Won</creator><creatorcontrib>Alelaumi, Shrouq ; Khader, Nourma ; He, Jingxi ; Lam, Sarah ; Yoon, Sang Won</creatorcontrib><description>•Enhance the stencil printing process performance by proper cleaning profile selection.•Residue buildup amount is a key criterion for stencil cleaning profile selection.•Image processing to quantify residue buildup amount on the stencil seating surface.•Recurrent neural network for accurate residue buildup prediction.
This research proposes a novel framework to control the stencil cleaning profile selection in the stencil printing process (SPP). The SPP is a major contributor to yield loss in surface mount technology (SMT). Enhancement in SPP performance is critical to improving the printed circuit board (PCB) assembly line. The selection of a solvent-based or a dry-based cleaning profile is challenging, but the choice determines the effectiveness and efficiency of the stencil cleaning operation. The amount of residue buildup under the stencil is the main criterion used to decide the appropriate cleaning profile in SPP. In this research, a multi-dimensional temporal recurrent neural network (RNN) approach is used to accurately predict the amount of residue buildup on the underneath surface of the stencil in real-time. Specifically, the long short-term memory (LSTM) architecture is trained using actual residue buildup data. The proposed LSTM prediction model is compared with other state-of-the-art regression models such as multilayer perceptron (MLP) and ensemble learning models. Experimental results show the proposed LSTM model outperforms the state-of-the-art regression models and accurately predicts the stencil status. The proposed research aids decision-makers in the SPP line to select the appropriate stencil cleaning profile adaptively and in real-time. As a result, the overall SPP performance is improved.</description><identifier>ISSN: 0736-5845</identifier><identifier>EISSN: 1879-2537</identifier><identifier>DOI: 10.1016/j.rcim.2020.102041</identifier><language>eng</language><publisher>Oxford: Elsevier Ltd</publisher><subject>Assembly lines ; Circuit boards ; Cleaning ; Cleaning profile selection ; Decision making ; Long short-term memory (LSTM) ; Multilayer perceptrons ; Neural networks ; Prediction models ; Printed circuits ; Real time ; Recurrent neural network (RNN) ; Recurrent neural networks ; Regression models ; Residues ; Stencil printing process</subject><ispartof>Robotics and computer-integrated manufacturing, 2021-04, Vol.68, p.102041, Article 102041</ispartof><rights>2020 Elsevier Ltd</rights><rights>Copyright Elsevier BV Apr 2021</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c328t-dc4612a211136e019d56303715012424b660b8750d796e925991067f7c93bc493</citedby><cites>FETCH-LOGICAL-c328t-dc4612a211136e019d56303715012424b660b8750d796e925991067f7c93bc493</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.rcim.2020.102041$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,780,784,3550,27924,27925,45995</link.rule.ids></links><search><creatorcontrib>Alelaumi, Shrouq</creatorcontrib><creatorcontrib>Khader, Nourma</creatorcontrib><creatorcontrib>He, Jingxi</creatorcontrib><creatorcontrib>Lam, Sarah</creatorcontrib><creatorcontrib>Yoon, Sang Won</creatorcontrib><title>Residue buildup predictive modeling for stencil cleaning profile decision-making using recurrent neural network</title><title>Robotics and computer-integrated manufacturing</title><description>•Enhance the stencil printing process performance by proper cleaning profile selection.•Residue buildup amount is a key criterion for stencil cleaning profile selection.•Image processing to quantify residue buildup amount on the stencil seating surface.•Recurrent neural network for accurate residue buildup prediction.
This research proposes a novel framework to control the stencil cleaning profile selection in the stencil printing process (SPP). The SPP is a major contributor to yield loss in surface mount technology (SMT). Enhancement in SPP performance is critical to improving the printed circuit board (PCB) assembly line. The selection of a solvent-based or a dry-based cleaning profile is challenging, but the choice determines the effectiveness and efficiency of the stencil cleaning operation. The amount of residue buildup under the stencil is the main criterion used to decide the appropriate cleaning profile in SPP. In this research, a multi-dimensional temporal recurrent neural network (RNN) approach is used to accurately predict the amount of residue buildup on the underneath surface of the stencil in real-time. Specifically, the long short-term memory (LSTM) architecture is trained using actual residue buildup data. The proposed LSTM prediction model is compared with other state-of-the-art regression models such as multilayer perceptron (MLP) and ensemble learning models. Experimental results show the proposed LSTM model outperforms the state-of-the-art regression models and accurately predicts the stencil status. The proposed research aids decision-makers in the SPP line to select the appropriate stencil cleaning profile adaptively and in real-time. As a result, the overall SPP performance is improved.</description><subject>Assembly lines</subject><subject>Circuit boards</subject><subject>Cleaning</subject><subject>Cleaning profile selection</subject><subject>Decision making</subject><subject>Long short-term memory (LSTM)</subject><subject>Multilayer perceptrons</subject><subject>Neural networks</subject><subject>Prediction models</subject><subject>Printed circuits</subject><subject>Real time</subject><subject>Recurrent neural network (RNN)</subject><subject>Recurrent neural networks</subject><subject>Regression models</subject><subject>Residues</subject><subject>Stencil printing process</subject><issn>0736-5845</issn><issn>1879-2537</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNp9kE1LxDAQhoMouK7-AU8Fz13z1aQBL7L4BQuC6Dm0yVTSbZuatCv-e1PWs5cZeJl35p0HoWuCNwQTcdtugnH9hmK6CBRzcoJWpJQqpwWTp2iFJRN5UfLiHF3E2GKMKS_YCvk3iM7OkNWz6-w8ZmMA68zkDpD13kLnhs-s8SGLEwzGdZnpoBoWcQy-cR1kFoyLzg95X-0XfY5LDWDmEGCYsgHmUHWpTd8-7C_RWVN1Ea7--hp9PD68b5_z3evTy_Z-lxtGyym3hgtCK0oIYQIwUbYQDDNJCkwop7wWAtelLLCVSoCihVIEC9lIo1htuGJrdHPcm2J-zRAn3fo5DOmkprwUpeBS4TRFj1Mm-BgDNHoMrq_CjyZYL2B1qxewegGrj2CT6e5ogpT_4CDoaFyCk7ilrydtvfvP_gtgF4GL</recordid><startdate>202104</startdate><enddate>202104</enddate><creator>Alelaumi, Shrouq</creator><creator>Khader, Nourma</creator><creator>He, Jingxi</creator><creator>Lam, Sarah</creator><creator>Yoon, Sang Won</creator><general>Elsevier Ltd</general><general>Elsevier BV</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7TB</scope><scope>8FD</scope><scope>FR3</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>202104</creationdate><title>Residue buildup predictive modeling for stencil cleaning profile decision-making using recurrent neural network</title><author>Alelaumi, Shrouq ; Khader, Nourma ; He, Jingxi ; Lam, Sarah ; Yoon, Sang Won</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c328t-dc4612a211136e019d56303715012424b660b8750d796e925991067f7c93bc493</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Assembly lines</topic><topic>Circuit boards</topic><topic>Cleaning</topic><topic>Cleaning profile selection</topic><topic>Decision making</topic><topic>Long short-term memory (LSTM)</topic><topic>Multilayer perceptrons</topic><topic>Neural networks</topic><topic>Prediction models</topic><topic>Printed circuits</topic><topic>Real time</topic><topic>Recurrent neural network (RNN)</topic><topic>Recurrent neural networks</topic><topic>Regression models</topic><topic>Residues</topic><topic>Stencil printing process</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Alelaumi, Shrouq</creatorcontrib><creatorcontrib>Khader, Nourma</creatorcontrib><creatorcontrib>He, Jingxi</creatorcontrib><creatorcontrib>Lam, Sarah</creatorcontrib><creatorcontrib>Yoon, Sang Won</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>Robotics and computer-integrated manufacturing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Alelaumi, Shrouq</au><au>Khader, Nourma</au><au>He, Jingxi</au><au>Lam, Sarah</au><au>Yoon, Sang Won</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Residue buildup predictive modeling for stencil cleaning profile decision-making using recurrent neural network</atitle><jtitle>Robotics and computer-integrated manufacturing</jtitle><date>2021-04</date><risdate>2021</risdate><volume>68</volume><spage>102041</spage><pages>102041-</pages><artnum>102041</artnum><issn>0736-5845</issn><eissn>1879-2537</eissn><abstract>•Enhance the stencil printing process performance by proper cleaning profile selection.•Residue buildup amount is a key criterion for stencil cleaning profile selection.•Image processing to quantify residue buildup amount on the stencil seating surface.•Recurrent neural network for accurate residue buildup prediction.
This research proposes a novel framework to control the stencil cleaning profile selection in the stencil printing process (SPP). The SPP is a major contributor to yield loss in surface mount technology (SMT). Enhancement in SPP performance is critical to improving the printed circuit board (PCB) assembly line. The selection of a solvent-based or a dry-based cleaning profile is challenging, but the choice determines the effectiveness and efficiency of the stencil cleaning operation. The amount of residue buildup under the stencil is the main criterion used to decide the appropriate cleaning profile in SPP. In this research, a multi-dimensional temporal recurrent neural network (RNN) approach is used to accurately predict the amount of residue buildup on the underneath surface of the stencil in real-time. Specifically, the long short-term memory (LSTM) architecture is trained using actual residue buildup data. The proposed LSTM prediction model is compared with other state-of-the-art regression models such as multilayer perceptron (MLP) and ensemble learning models. Experimental results show the proposed LSTM model outperforms the state-of-the-art regression models and accurately predicts the stencil status. The proposed research aids decision-makers in the SPP line to select the appropriate stencil cleaning profile adaptively and in real-time. As a result, the overall SPP performance is improved.</abstract><cop>Oxford</cop><pub>Elsevier Ltd</pub><doi>10.1016/j.rcim.2020.102041</doi></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0736-5845 |
ispartof | Robotics and computer-integrated manufacturing, 2021-04, Vol.68, p.102041, Article 102041 |
issn | 0736-5845 1879-2537 |
language | eng |
recordid | cdi_proquest_journals_2486864790 |
source | Access via ScienceDirect (Elsevier) |
subjects | Assembly lines Circuit boards Cleaning Cleaning profile selection Decision making Long short-term memory (LSTM) Multilayer perceptrons Neural networks Prediction models Printed circuits Real time Recurrent neural network (RNN) Recurrent neural networks Regression models Residues Stencil printing process |
title | Residue buildup predictive modeling for stencil cleaning profile decision-making using recurrent neural network |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T18%3A16%3A49IST&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=Residue%20buildup%20predictive%20modeling%20for%20stencil%20cleaning%20profile%20decision-making%20using%20recurrent%20neural%20network&rft.jtitle=Robotics%20and%20computer-integrated%20manufacturing&rft.au=Alelaumi,%20Shrouq&rft.date=2021-04&rft.volume=68&rft.spage=102041&rft.pages=102041-&rft.artnum=102041&rft.issn=0736-5845&rft.eissn=1879-2537&rft_id=info:doi/10.1016/j.rcim.2020.102041&rft_dat=%3Cproquest_cross%3E2486864790%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=2486864790&rft_id=info:pmid/&rft_els_id=S0736584520302520&rfr_iscdi=true |