Adhesion Testing System Based on Convolutional Neural Networks for Quality Inspection of Flexible Strain Sensors
Manufacturing reliable strain sensors based on nanostructured materials faces several challenges, such as ensuring quality inspection of the adhesion between the active sensor and its substrate. In order to overcome this, the use of a deep learning-based technique is proposed herein to determine the...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on industrial informatics 2024-07, Vol.20 (7), p.9235-9243 |
|---|---|
| Hauptverfasser: | , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 9243 |
|---|---|
| container_issue | 7 |
| container_start_page | 9235 |
| container_title | IEEE transactions on industrial informatics |
| container_volume | 20 |
| creator | Isaac Medina, Ignacio Arana, Gabriel Castillo Atoche, Andrea Cecilia Estrada Lopez, Johan Jair Vazquez Castillo, Javier Aviles, Francis Castillo Atoche, Alejandro Arturo |
| description | Manufacturing reliable strain sensors based on nanostructured materials faces several challenges, such as ensuring quality inspection of the adhesion between the active sensor and its substrate. In order to overcome this, the use of a deep learning-based technique is proposed herein to determine the in-situ adhesion strength. This study conducts an adhesion strength analysis between carbon nanotubes (CNTs) over a polymeric substrate (as components of a strain sensor), using image analysis. In line with the edge-computing paradigm, a novel inspection system is presented. An embedded processor equipped with a convolutional neural network architecture is used to inspect the CNT adhesion deposited on a substrate surface using deep learning semantic segmentation. This determines the relative concentration of CNTs covering the peeled area and its spatial probabilistic distribution map. Experimental results demonstrate the quality inspection precision, both before and after peeling-tape tests with an accuracy of up to 96.56%. |
| doi_str_mv | 10.1109/TII.2024.3383547 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_10499719</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10499719</ieee_id><sourcerecordid>3075426485</sourcerecordid><originalsourceid>FETCH-LOGICAL-c245t-b4f59563d8a8fcb61000350ab6f8b6da66d62621181d5c647d6dc81476983dbc3</originalsourceid><addsrcrecordid>eNpNkL1PwzAQxS0EEqWwMzBYYk6x44_YY6koRKpAqGW2nNiBlDQOdlLof49LOzC90-n3TvceANcYTTBG8m6V55MUpXRCiCCMZidghCXFCUIMncaZMZyQFJFzcBHCGiGSISJHoJuaDxtq18KVDX3dvsPlLvR2A-91sAbG_cy1W9cMfWR0A5_t4P-k_3b-M8DKefg66KbudzBvQ2fLPQhdBeeN_amLxsJl73XdwqVtg_PhEpxVugn26qhj8DZ_WM2eksXLYz6bLpIypaxPCloxyTgxQouqLDhG8WWGdMErUXCjOTc85SnGAhtWcpoZbkqBacalIKYoyRjcHu523n0NMZtau8HHCEERlDGacipYpNCBKr0LwdtKdb7eaL9TGKl9ryr2qva9qmOv0XJzsNTW2n84lTLDkvwCFAp0zQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3075426485</pqid></control><display><type>article</type><title>Adhesion Testing System Based on Convolutional Neural Networks for Quality Inspection of Flexible Strain Sensors</title><source>IEEE Electronic Library (IEL)</source><creator>Isaac Medina, Ignacio ; Arana, Gabriel ; Castillo Atoche, Andrea Cecilia ; Estrada Lopez, Johan Jair ; Vazquez Castillo, Javier ; Aviles, Francis ; Castillo Atoche, Alejandro Arturo</creator><creatorcontrib>Isaac Medina, Ignacio ; Arana, Gabriel ; Castillo Atoche, Andrea Cecilia ; Estrada Lopez, Johan Jair ; Vazquez Castillo, Javier ; Aviles, Francis ; Castillo Atoche, Alejandro Arturo</creatorcontrib><description>Manufacturing reliable strain sensors based on nanostructured materials faces several challenges, such as ensuring quality inspection of the adhesion between the active sensor and its substrate. In order to overcome this, the use of a deep learning-based technique is proposed herein to determine the in-situ adhesion strength. This study conducts an adhesion strength analysis between carbon nanotubes (CNTs) over a polymeric substrate (as components of a strain sensor), using image analysis. In line with the edge-computing paradigm, a novel inspection system is presented. An embedded processor equipped with a convolutional neural network architecture is used to inspect the CNT adhesion deposited on a substrate surface using deep learning semantic segmentation. This determines the relative concentration of CNTs covering the peeled area and its spatial probabilistic distribution map. Experimental results demonstrate the quality inspection precision, both before and after peeling-tape tests with an accuracy of up to 96.56%.</description><identifier>ISSN: 1551-3203</identifier><identifier>EISSN: 1941-0050</identifier><identifier>DOI: 10.1109/TII.2024.3383547</identifier><identifier>CODEN: ITIICH</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Adhesion quality inspection ; Adhesion tests ; Adhesive strength ; Adhesives ; Artificial neural networks ; Capacitive sensors ; Carbon nanotubes ; Computer architecture ; convolutional neural network (CNN) ; Deep learning ; Edge computing ; Effectiveness ; flexible strain sensor ; Image analysis ; Inspection ; Microprocessors ; Nanostructured materials ; Semantic segmentation ; Sensors ; Substrates ; Testing</subject><ispartof>IEEE transactions on industrial informatics, 2024-07, Vol.20 (7), p.9235-9243</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024</rights><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c245t-b4f59563d8a8fcb61000350ab6f8b6da66d62621181d5c647d6dc81476983dbc3</cites><orcidid>0000-0003-0440-5796 ; 0009-0007-4592-8135 ; 0000-0002-0227-1758 ; 0000-0001-9489-6386 ; 0000-0002-0465-8948 ; 0000-0002-0956-5994 ; 0000-0002-6064-0371</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10499719$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,776,780,792,27901,27902,54733</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10499719$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Isaac Medina, Ignacio</creatorcontrib><creatorcontrib>Arana, Gabriel</creatorcontrib><creatorcontrib>Castillo Atoche, Andrea Cecilia</creatorcontrib><creatorcontrib>Estrada Lopez, Johan Jair</creatorcontrib><creatorcontrib>Vazquez Castillo, Javier</creatorcontrib><creatorcontrib>Aviles, Francis</creatorcontrib><creatorcontrib>Castillo Atoche, Alejandro Arturo</creatorcontrib><title>Adhesion Testing System Based on Convolutional Neural Networks for Quality Inspection of Flexible Strain Sensors</title><title>IEEE transactions on industrial informatics</title><addtitle>TII</addtitle><description>Manufacturing reliable strain sensors based on nanostructured materials faces several challenges, such as ensuring quality inspection of the adhesion between the active sensor and its substrate. In order to overcome this, the use of a deep learning-based technique is proposed herein to determine the in-situ adhesion strength. This study conducts an adhesion strength analysis between carbon nanotubes (CNTs) over a polymeric substrate (as components of a strain sensor), using image analysis. In line with the edge-computing paradigm, a novel inspection system is presented. An embedded processor equipped with a convolutional neural network architecture is used to inspect the CNT adhesion deposited on a substrate surface using deep learning semantic segmentation. This determines the relative concentration of CNTs covering the peeled area and its spatial probabilistic distribution map. Experimental results demonstrate the quality inspection precision, both before and after peeling-tape tests with an accuracy of up to 96.56%.</description><subject>Adhesion quality inspection</subject><subject>Adhesion tests</subject><subject>Adhesive strength</subject><subject>Adhesives</subject><subject>Artificial neural networks</subject><subject>Capacitive sensors</subject><subject>Carbon nanotubes</subject><subject>Computer architecture</subject><subject>convolutional neural network (CNN)</subject><subject>Deep learning</subject><subject>Edge computing</subject><subject>Effectiveness</subject><subject>flexible strain sensor</subject><subject>Image analysis</subject><subject>Inspection</subject><subject>Microprocessors</subject><subject>Nanostructured materials</subject><subject>Semantic segmentation</subject><subject>Sensors</subject><subject>Substrates</subject><subject>Testing</subject><issn>1551-3203</issn><issn>1941-0050</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpNkL1PwzAQxS0EEqWwMzBYYk6x44_YY6koRKpAqGW2nNiBlDQOdlLof49LOzC90-n3TvceANcYTTBG8m6V55MUpXRCiCCMZidghCXFCUIMncaZMZyQFJFzcBHCGiGSISJHoJuaDxtq18KVDX3dvsPlLvR2A-91sAbG_cy1W9cMfWR0A5_t4P-k_3b-M8DKefg66KbudzBvQ2fLPQhdBeeN_amLxsJl73XdwqVtg_PhEpxVugn26qhj8DZ_WM2eksXLYz6bLpIypaxPCloxyTgxQouqLDhG8WWGdMErUXCjOTc85SnGAhtWcpoZbkqBacalIKYoyRjcHu523n0NMZtau8HHCEERlDGacipYpNCBKr0LwdtKdb7eaL9TGKl9ryr2qva9qmOv0XJzsNTW2n84lTLDkvwCFAp0zQ</recordid><startdate>20240701</startdate><enddate>20240701</enddate><creator>Isaac Medina, Ignacio</creator><creator>Arana, Gabriel</creator><creator>Castillo Atoche, Andrea Cecilia</creator><creator>Estrada Lopez, Johan Jair</creator><creator>Vazquez Castillo, Javier</creator><creator>Aviles, Francis</creator><creator>Castillo Atoche, Alejandro Arturo</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>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0003-0440-5796</orcidid><orcidid>https://orcid.org/0009-0007-4592-8135</orcidid><orcidid>https://orcid.org/0000-0002-0227-1758</orcidid><orcidid>https://orcid.org/0000-0001-9489-6386</orcidid><orcidid>https://orcid.org/0000-0002-0465-8948</orcidid><orcidid>https://orcid.org/0000-0002-0956-5994</orcidid><orcidid>https://orcid.org/0000-0002-6064-0371</orcidid></search><sort><creationdate>20240701</creationdate><title>Adhesion Testing System Based on Convolutional Neural Networks for Quality Inspection of Flexible Strain Sensors</title><author>Isaac Medina, Ignacio ; Arana, Gabriel ; Castillo Atoche, Andrea Cecilia ; Estrada Lopez, Johan Jair ; Vazquez Castillo, Javier ; Aviles, Francis ; Castillo Atoche, Alejandro Arturo</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c245t-b4f59563d8a8fcb61000350ab6f8b6da66d62621181d5c647d6dc81476983dbc3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Adhesion quality inspection</topic><topic>Adhesion tests</topic><topic>Adhesive strength</topic><topic>Adhesives</topic><topic>Artificial neural networks</topic><topic>Capacitive sensors</topic><topic>Carbon nanotubes</topic><topic>Computer architecture</topic><topic>convolutional neural network (CNN)</topic><topic>Deep learning</topic><topic>Edge computing</topic><topic>Effectiveness</topic><topic>flexible strain sensor</topic><topic>Image analysis</topic><topic>Inspection</topic><topic>Microprocessors</topic><topic>Nanostructured materials</topic><topic>Semantic segmentation</topic><topic>Sensors</topic><topic>Substrates</topic><topic>Testing</topic><toplevel>online_resources</toplevel><creatorcontrib>Isaac Medina, Ignacio</creatorcontrib><creatorcontrib>Arana, Gabriel</creatorcontrib><creatorcontrib>Castillo Atoche, Andrea Cecilia</creatorcontrib><creatorcontrib>Estrada Lopez, Johan Jair</creatorcontrib><creatorcontrib>Vazquez Castillo, Javier</creatorcontrib><creatorcontrib>Aviles, Francis</creatorcontrib><creatorcontrib>Castillo Atoche, Alejandro Arturo</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>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology 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>IEEE transactions on industrial informatics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Isaac Medina, Ignacio</au><au>Arana, Gabriel</au><au>Castillo Atoche, Andrea Cecilia</au><au>Estrada Lopez, Johan Jair</au><au>Vazquez Castillo, Javier</au><au>Aviles, Francis</au><au>Castillo Atoche, Alejandro Arturo</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Adhesion Testing System Based on Convolutional Neural Networks for Quality Inspection of Flexible Strain Sensors</atitle><jtitle>IEEE transactions on industrial informatics</jtitle><stitle>TII</stitle><date>2024-07-01</date><risdate>2024</risdate><volume>20</volume><issue>7</issue><spage>9235</spage><epage>9243</epage><pages>9235-9243</pages><issn>1551-3203</issn><eissn>1941-0050</eissn><coden>ITIICH</coden><abstract>Manufacturing reliable strain sensors based on nanostructured materials faces several challenges, such as ensuring quality inspection of the adhesion between the active sensor and its substrate. In order to overcome this, the use of a deep learning-based technique is proposed herein to determine the in-situ adhesion strength. This study conducts an adhesion strength analysis between carbon nanotubes (CNTs) over a polymeric substrate (as components of a strain sensor), using image analysis. In line with the edge-computing paradigm, a novel inspection system is presented. An embedded processor equipped with a convolutional neural network architecture is used to inspect the CNT adhesion deposited on a substrate surface using deep learning semantic segmentation. This determines the relative concentration of CNTs covering the peeled area and its spatial probabilistic distribution map. Experimental results demonstrate the quality inspection precision, both before and after peeling-tape tests with an accuracy of up to 96.56%.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/TII.2024.3383547</doi><tpages>9</tpages><orcidid>https://orcid.org/0000-0003-0440-5796</orcidid><orcidid>https://orcid.org/0009-0007-4592-8135</orcidid><orcidid>https://orcid.org/0000-0002-0227-1758</orcidid><orcidid>https://orcid.org/0000-0001-9489-6386</orcidid><orcidid>https://orcid.org/0000-0002-0465-8948</orcidid><orcidid>https://orcid.org/0000-0002-0956-5994</orcidid><orcidid>https://orcid.org/0000-0002-6064-0371</orcidid></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1551-3203 |
| ispartof | IEEE transactions on industrial informatics, 2024-07, Vol.20 (7), p.9235-9243 |
| issn | 1551-3203 1941-0050 |
| language | eng |
| recordid | cdi_ieee_primary_10499719 |
| source | IEEE Electronic Library (IEL) |
| subjects | Adhesion quality inspection Adhesion tests Adhesive strength Adhesives Artificial neural networks Capacitive sensors Carbon nanotubes Computer architecture convolutional neural network (CNN) Deep learning Edge computing Effectiveness flexible strain sensor Image analysis Inspection Microprocessors Nanostructured materials Semantic segmentation Sensors Substrates Testing |
| title | Adhesion Testing System Based on Convolutional Neural Networks for Quality Inspection of Flexible Strain Sensors |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-06T04%3A56%3A03IST&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=Adhesion%20Testing%20System%20Based%20on%20Convolutional%20Neural%20Networks%20for%20Quality%20Inspection%20of%20Flexible%20Strain%20Sensors&rft.jtitle=IEEE%20transactions%20on%20industrial%20informatics&rft.au=Isaac%20Medina,%20Ignacio&rft.date=2024-07-01&rft.volume=20&rft.issue=7&rft.spage=9235&rft.epage=9243&rft.pages=9235-9243&rft.issn=1551-3203&rft.eissn=1941-0050&rft.coden=ITIICH&rft_id=info:doi/10.1109/TII.2024.3383547&rft_dat=%3Cproquest_RIE%3E3075426485%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=3075426485&rft_id=info:pmid/&rft_ieee_id=10499719&rfr_iscdi=true |