Bending recognition based on learning enhanced fiber specklegram sensor

In this paper, we propose and demonstrate a deep learning-enhanced fiber specklegram sensor for bending recognition. A segment of multimode fiber is used to sense bending, and tiny bending changes lead to significant variations in the speckle pattern generated at the distal end of the fiber. Princip...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Measurement science & technology 2023-11, Vol.34 (11), p.115125
Hauptverfasser: Gao, Han, Zhang, Yan-Xin, Zhang, Wei-Gang, Yan, Tie-Yi
Format: Artikel
Sprache:eng
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue 11
container_start_page 115125
container_title Measurement science & technology
container_volume 34
creator Gao, Han
Zhang, Yan-Xin
Zhang, Wei-Gang
Yan, Tie-Yi
description In this paper, we propose and demonstrate a deep learning-enhanced fiber specklegram sensor for bending recognition. A segment of multimode fiber is used to sense bending, and tiny bending changes lead to significant variations in the speckle pattern generated at the distal end of the fiber. Principal component analysis (PCA) is utilized to optimize the collected samples and remove noise and redundant information by mining internal features, which makes the mapping relationship between the speckle image and corresponding curvature clearer and is conducive to reducing computational complexity. Back propagation neural network is employed to learn the mapping relationship between speckle image and curvature on the optimized dataset according to the optimized direction provided by PCA. The testing results show that the prediction error of the trained model for the learned bending state is 5.9 × 10 −4 m −1 , and the prediction speed is 0.05 ms per frame. The proposed scheme has a strong generalization ability and can be applied to predict bending states that have never been learned or seen with a prediction error of 3.8 × 10 −2 m −1 , which cannot be realized by the previously reported fiber specklegram sensor based on the classification neural network. The bending recognition scheme enhanced by deep learning proposed in this paper provides an enlightening reference for solving fiber sensing problems with deep learning methods, and it has the potential to be applied in more fields as a general scheme.
doi_str_mv 10.1088/1361-6501/acea99
format Article
fullrecord <record><control><sourceid>crossref</sourceid><recordid>TN_cdi_crossref_primary_10_1088_1361_6501_acea99</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>10_1088_1361_6501_acea99</sourcerecordid><originalsourceid>FETCH-LOGICAL-c243t-178ed138bbfce4381154ee652dbea956ed3f073c21cffe310b1f782174dbb2823</originalsourceid><addsrcrecordid>eNo9UE1PwzAUixBIlMGdY_9A2XtJ26RHmGBDmsQFzlE-XkqhS6dkF_49rYY42bIlyzZj9wgPCEqtUbRYtQ3g2jgyXXfBin_pkhXQNbICLsQ1u8n5CwAkdF3Btk8U_RD7MpGb-jichimW1mTy5UxGMikuLsVPE90shsFSKvOR3PdIfTKHMlPMU7plV8GMme7-cMU-Xp7fN7tq_7Z93TzuK8drcapQKvIolLXBUS0UYlMTtQ33di7dtORFACkcRxcCCQSLQSqOsvbWcsXFisE516Up50RBH9NwMOlHI-jlCL2s1stqfT5C_AJhj1K1</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Bending recognition based on learning enhanced fiber specklegram sensor</title><source>IOP Publishing Journals</source><source>Institute of Physics (IOP) Journals - HEAL-Link</source><creator>Gao, Han ; Zhang, Yan-Xin ; Zhang, Wei-Gang ; Yan, Tie-Yi</creator><creatorcontrib>Gao, Han ; Zhang, Yan-Xin ; Zhang, Wei-Gang ; Yan, Tie-Yi</creatorcontrib><description>In this paper, we propose and demonstrate a deep learning-enhanced fiber specklegram sensor for bending recognition. A segment of multimode fiber is used to sense bending, and tiny bending changes lead to significant variations in the speckle pattern generated at the distal end of the fiber. Principal component analysis (PCA) is utilized to optimize the collected samples and remove noise and redundant information by mining internal features, which makes the mapping relationship between the speckle image and corresponding curvature clearer and is conducive to reducing computational complexity. Back propagation neural network is employed to learn the mapping relationship between speckle image and curvature on the optimized dataset according to the optimized direction provided by PCA. The testing results show that the prediction error of the trained model for the learned bending state is 5.9 × 10 −4 m −1 , and the prediction speed is 0.05 ms per frame. The proposed scheme has a strong generalization ability and can be applied to predict bending states that have never been learned or seen with a prediction error of 3.8 × 10 −2 m −1 , which cannot be realized by the previously reported fiber specklegram sensor based on the classification neural network. The bending recognition scheme enhanced by deep learning proposed in this paper provides an enlightening reference for solving fiber sensing problems with deep learning methods, and it has the potential to be applied in more fields as a general scheme.</description><identifier>ISSN: 0957-0233</identifier><identifier>EISSN: 1361-6501</identifier><identifier>DOI: 10.1088/1361-6501/acea99</identifier><language>eng</language><ispartof>Measurement science &amp; technology, 2023-11, Vol.34 (11), p.115125</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c243t-178ed138bbfce4381154ee652dbea956ed3f073c21cffe310b1f782174dbb2823</citedby><cites>FETCH-LOGICAL-c243t-178ed138bbfce4381154ee652dbea956ed3f073c21cffe310b1f782174dbb2823</cites><orcidid>0000-0002-9465-9783 ; 0000-0003-2896-9852</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>315,782,786,27931,27932</link.rule.ids></links><search><creatorcontrib>Gao, Han</creatorcontrib><creatorcontrib>Zhang, Yan-Xin</creatorcontrib><creatorcontrib>Zhang, Wei-Gang</creatorcontrib><creatorcontrib>Yan, Tie-Yi</creatorcontrib><title>Bending recognition based on learning enhanced fiber specklegram sensor</title><title>Measurement science &amp; technology</title><description>In this paper, we propose and demonstrate a deep learning-enhanced fiber specklegram sensor for bending recognition. A segment of multimode fiber is used to sense bending, and tiny bending changes lead to significant variations in the speckle pattern generated at the distal end of the fiber. Principal component analysis (PCA) is utilized to optimize the collected samples and remove noise and redundant information by mining internal features, which makes the mapping relationship between the speckle image and corresponding curvature clearer and is conducive to reducing computational complexity. Back propagation neural network is employed to learn the mapping relationship between speckle image and curvature on the optimized dataset according to the optimized direction provided by PCA. The testing results show that the prediction error of the trained model for the learned bending state is 5.9 × 10 −4 m −1 , and the prediction speed is 0.05 ms per frame. The proposed scheme has a strong generalization ability and can be applied to predict bending states that have never been learned or seen with a prediction error of 3.8 × 10 −2 m −1 , which cannot be realized by the previously reported fiber specklegram sensor based on the classification neural network. The bending recognition scheme enhanced by deep learning proposed in this paper provides an enlightening reference for solving fiber sensing problems with deep learning methods, and it has the potential to be applied in more fields as a general scheme.</description><issn>0957-0233</issn><issn>1361-6501</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><recordid>eNo9UE1PwzAUixBIlMGdY_9A2XtJ26RHmGBDmsQFzlE-XkqhS6dkF_49rYY42bIlyzZj9wgPCEqtUbRYtQ3g2jgyXXfBin_pkhXQNbICLsQ1u8n5CwAkdF3Btk8U_RD7MpGb-jichimW1mTy5UxGMikuLsVPE90shsFSKvOR3PdIfTKHMlPMU7plV8GMme7-cMU-Xp7fN7tq_7Z93TzuK8drcapQKvIolLXBUS0UYlMTtQ33di7dtORFACkcRxcCCQSLQSqOsvbWcsXFisE516Up50RBH9NwMOlHI-jlCL2s1stqfT5C_AJhj1K1</recordid><startdate>20231101</startdate><enddate>20231101</enddate><creator>Gao, Han</creator><creator>Zhang, Yan-Xin</creator><creator>Zhang, Wei-Gang</creator><creator>Yan, Tie-Yi</creator><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0002-9465-9783</orcidid><orcidid>https://orcid.org/0000-0003-2896-9852</orcidid></search><sort><creationdate>20231101</creationdate><title>Bending recognition based on learning enhanced fiber specklegram sensor</title><author>Gao, Han ; Zhang, Yan-Xin ; Zhang, Wei-Gang ; Yan, Tie-Yi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c243t-178ed138bbfce4381154ee652dbea956ed3f073c21cffe310b1f782174dbb2823</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Gao, Han</creatorcontrib><creatorcontrib>Zhang, Yan-Xin</creatorcontrib><creatorcontrib>Zhang, Wei-Gang</creatorcontrib><creatorcontrib>Yan, Tie-Yi</creatorcontrib><collection>CrossRef</collection><jtitle>Measurement science &amp; technology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Gao, Han</au><au>Zhang, Yan-Xin</au><au>Zhang, Wei-Gang</au><au>Yan, Tie-Yi</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Bending recognition based on learning enhanced fiber specklegram sensor</atitle><jtitle>Measurement science &amp; technology</jtitle><date>2023-11-01</date><risdate>2023</risdate><volume>34</volume><issue>11</issue><spage>115125</spage><pages>115125-</pages><issn>0957-0233</issn><eissn>1361-6501</eissn><abstract>In this paper, we propose and demonstrate a deep learning-enhanced fiber specklegram sensor for bending recognition. A segment of multimode fiber is used to sense bending, and tiny bending changes lead to significant variations in the speckle pattern generated at the distal end of the fiber. Principal component analysis (PCA) is utilized to optimize the collected samples and remove noise and redundant information by mining internal features, which makes the mapping relationship between the speckle image and corresponding curvature clearer and is conducive to reducing computational complexity. Back propagation neural network is employed to learn the mapping relationship between speckle image and curvature on the optimized dataset according to the optimized direction provided by PCA. The testing results show that the prediction error of the trained model for the learned bending state is 5.9 × 10 −4 m −1 , and the prediction speed is 0.05 ms per frame. The proposed scheme has a strong generalization ability and can be applied to predict bending states that have never been learned or seen with a prediction error of 3.8 × 10 −2 m −1 , which cannot be realized by the previously reported fiber specklegram sensor based on the classification neural network. The bending recognition scheme enhanced by deep learning proposed in this paper provides an enlightening reference for solving fiber sensing problems with deep learning methods, and it has the potential to be applied in more fields as a general scheme.</abstract><doi>10.1088/1361-6501/acea99</doi><orcidid>https://orcid.org/0000-0002-9465-9783</orcidid><orcidid>https://orcid.org/0000-0003-2896-9852</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 0957-0233
ispartof Measurement science & technology, 2023-11, Vol.34 (11), p.115125
issn 0957-0233
1361-6501
language eng
recordid cdi_crossref_primary_10_1088_1361_6501_acea99
source IOP Publishing Journals; Institute of Physics (IOP) Journals - HEAL-Link
title Bending recognition based on learning enhanced fiber specklegram sensor
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-05T23%3A06%3A23IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-crossref&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Bending%20recognition%20based%20on%20learning%20enhanced%20fiber%20specklegram%20sensor&rft.jtitle=Measurement%20science%20&%20technology&rft.au=Gao,%20Han&rft.date=2023-11-01&rft.volume=34&rft.issue=11&rft.spage=115125&rft.pages=115125-&rft.issn=0957-0233&rft.eissn=1361-6501&rft_id=info:doi/10.1088/1361-6501/acea99&rft_dat=%3Ccrossref%3E10_1088_1361_6501_acea99%3C/crossref%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