U-Net convolutional neural network-based modification method for precise fabrication of three-dimensional microstructures using laser direct writing lithography

In this paper, a modification method based on a U-Net convolutional neural network is proposed for the precise fabrication of three-dimensional microstructures using laser direct writing lithography (LDWL). In order to build the correspondence between the exposure intensity distribution data importe...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Optics express 2021-02, Vol.29 (4), p.6236-6247
Hauptverfasser: Sun, Xiuhui, Yin, Shaoyun, Jiang, Haibo, Zhang, Weiguo, Gao, Mingyou, Du, Jinglei, Du, Chunlei
Format: Artikel
Sprache:eng
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 6247
container_issue 4
container_start_page 6236
container_title Optics express
container_volume 29
creator Sun, Xiuhui
Yin, Shaoyun
Jiang, Haibo
Zhang, Weiguo
Gao, Mingyou
Du, Jinglei
Du, Chunlei
description In this paper, a modification method based on a U-Net convolutional neural network is proposed for the precise fabrication of three-dimensional microstructures using laser direct writing lithography (LDWL). In order to build the correspondence between the exposure intensity distribution data imported to the laser direct writing system and the surface profile data of the actual fabricated microstructure, these two kinds of data are used as training tensors of the U-Net convolutional neural network, which is proved to be capable of generating their accurate mapping relations. By employing such mapping relations to modify the initial designed exposure intensity data of the parabolic and saddle concave micro-lens with an aperture of 24µm×24µm, it is demonstrated that their fabrication precision, characterized by the mean squared error (MSE) and the peak signal-to-noise ratio (PSNR) between the fabricated and the designed microstructure, can be improved significantly. Specifically, the MSE of the parabolic and saddle concave micro-lens decreased from 100 to 17 and 151 to 50, respectively, and the PSNR increased from 22dB to 29dB and 20dB to 25dB, respectively. Furthermore, the effect of laser beam shaping using these two kinds of micro-lens has also been improved considerably. This study provides a new solution for the fabrication of high-precision three-dimensional microstructures by LDWL.
doi_str_mv 10.1364/OE.416871
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2502205901</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2502205901</sourcerecordid><originalsourceid>FETCH-LOGICAL-c320t-d3230082f6b32f6deedff09520a5e5182243045344e15d946cbdd51a0f2a66a53</originalsourceid><addsrcrecordid>eNpNkctOwzAQRS0EolBY8APIS1ik-Jk0S4TKQ6rohq4jJx63hiQutgPib_hU0oYiNjOjmaMjjS5CF5RMKE_FzWI2ETSdZvQAnVCSi0SQaXb4bx6h0xBeCaEiy7NjNOI8YykV-Qn6XibPEHHl2g9Xd9G6VtW4hc7vWvx0_i0pVQCNG6etsZXaMriBuHYaG-fxxkNlA2CjSr8_O4Pj2gMk2jbQhsHa2Mq7EH1Xxc5DwF2w7QrXvdxjbXtLxJ_ext3S9vqVV5v11xk6MqoOcP7bx2h5P3u5e0zmi4enu9t5UnFGYqI544RMmUlL3hcNoI0huWRESZB0ypjgREguBFCpc5FWpdaSKmKYSlMl-RhdDd6Nd-8dhFg0NlRQ16oF14WCScIYkTmhPXo9oNt_ggdTbLxtlP8qKCm2gRSLWTEE0rOXv9qubED_kfsE-A-s-Iob</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2502205901</pqid></control><display><type>article</type><title>U-Net convolutional neural network-based modification method for precise fabrication of three-dimensional microstructures using laser direct writing lithography</title><source>DOAJ Directory of Open Access Journals</source><source>EZB-FREE-00999 freely available EZB journals</source><source>Alma/SFX Local Collection</source><creator>Sun, Xiuhui ; Yin, Shaoyun ; Jiang, Haibo ; Zhang, Weiguo ; Gao, Mingyou ; Du, Jinglei ; Du, Chunlei</creator><creatorcontrib>Sun, Xiuhui ; Yin, Shaoyun ; Jiang, Haibo ; Zhang, Weiguo ; Gao, Mingyou ; Du, Jinglei ; Du, Chunlei</creatorcontrib><description>In this paper, a modification method based on a U-Net convolutional neural network is proposed for the precise fabrication of three-dimensional microstructures using laser direct writing lithography (LDWL). In order to build the correspondence between the exposure intensity distribution data imported to the laser direct writing system and the surface profile data of the actual fabricated microstructure, these two kinds of data are used as training tensors of the U-Net convolutional neural network, which is proved to be capable of generating their accurate mapping relations. By employing such mapping relations to modify the initial designed exposure intensity data of the parabolic and saddle concave micro-lens with an aperture of 24µm×24µm, it is demonstrated that their fabrication precision, characterized by the mean squared error (MSE) and the peak signal-to-noise ratio (PSNR) between the fabricated and the designed microstructure, can be improved significantly. Specifically, the MSE of the parabolic and saddle concave micro-lens decreased from 100 to 17 and 151 to 50, respectively, and the PSNR increased from 22dB to 29dB and 20dB to 25dB, respectively. Furthermore, the effect of laser beam shaping using these two kinds of micro-lens has also been improved considerably. This study provides a new solution for the fabrication of high-precision three-dimensional microstructures by LDWL.</description><identifier>ISSN: 1094-4087</identifier><identifier>EISSN: 1094-4087</identifier><identifier>DOI: 10.1364/OE.416871</identifier><identifier>PMID: 33726149</identifier><language>eng</language><publisher>United States</publisher><ispartof>Optics express, 2021-02, Vol.29 (4), p.6236-6247</ispartof><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c320t-d3230082f6b32f6deedff09520a5e5182243045344e15d946cbdd51a0f2a66a53</citedby><cites>FETCH-LOGICAL-c320t-d3230082f6b32f6deedff09520a5e5182243045344e15d946cbdd51a0f2a66a53</cites><orcidid>0000-0002-2596-7010</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,864,27924,27925</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/33726149$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Sun, Xiuhui</creatorcontrib><creatorcontrib>Yin, Shaoyun</creatorcontrib><creatorcontrib>Jiang, Haibo</creatorcontrib><creatorcontrib>Zhang, Weiguo</creatorcontrib><creatorcontrib>Gao, Mingyou</creatorcontrib><creatorcontrib>Du, Jinglei</creatorcontrib><creatorcontrib>Du, Chunlei</creatorcontrib><title>U-Net convolutional neural network-based modification method for precise fabrication of three-dimensional microstructures using laser direct writing lithography</title><title>Optics express</title><addtitle>Opt Express</addtitle><description>In this paper, a modification method based on a U-Net convolutional neural network is proposed for the precise fabrication of three-dimensional microstructures using laser direct writing lithography (LDWL). In order to build the correspondence between the exposure intensity distribution data imported to the laser direct writing system and the surface profile data of the actual fabricated microstructure, these two kinds of data are used as training tensors of the U-Net convolutional neural network, which is proved to be capable of generating their accurate mapping relations. By employing such mapping relations to modify the initial designed exposure intensity data of the parabolic and saddle concave micro-lens with an aperture of 24µm×24µm, it is demonstrated that their fabrication precision, characterized by the mean squared error (MSE) and the peak signal-to-noise ratio (PSNR) between the fabricated and the designed microstructure, can be improved significantly. Specifically, the MSE of the parabolic and saddle concave micro-lens decreased from 100 to 17 and 151 to 50, respectively, and the PSNR increased from 22dB to 29dB and 20dB to 25dB, respectively. Furthermore, the effect of laser beam shaping using these two kinds of micro-lens has also been improved considerably. This study provides a new solution for the fabrication of high-precision three-dimensional microstructures by LDWL.</description><issn>1094-4087</issn><issn>1094-4087</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNpNkctOwzAQRS0EolBY8APIS1ik-Jk0S4TKQ6rohq4jJx63hiQutgPib_hU0oYiNjOjmaMjjS5CF5RMKE_FzWI2ETSdZvQAnVCSi0SQaXb4bx6h0xBeCaEiy7NjNOI8YykV-Qn6XibPEHHl2g9Xd9G6VtW4hc7vWvx0_i0pVQCNG6etsZXaMriBuHYaG-fxxkNlA2CjSr8_O4Pj2gMk2jbQhsHa2Mq7EH1Xxc5DwF2w7QrXvdxjbXtLxJ_ext3S9vqVV5v11xk6MqoOcP7bx2h5P3u5e0zmi4enu9t5UnFGYqI544RMmUlL3hcNoI0huWRESZB0ypjgREguBFCpc5FWpdaSKmKYSlMl-RhdDd6Nd-8dhFg0NlRQ16oF14WCScIYkTmhPXo9oNt_ggdTbLxtlP8qKCm2gRSLWTEE0rOXv9qubED_kfsE-A-s-Iob</recordid><startdate>20210215</startdate><enddate>20210215</enddate><creator>Sun, Xiuhui</creator><creator>Yin, Shaoyun</creator><creator>Jiang, Haibo</creator><creator>Zhang, Weiguo</creator><creator>Gao, Mingyou</creator><creator>Du, Jinglei</creator><creator>Du, Chunlei</creator><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-2596-7010</orcidid></search><sort><creationdate>20210215</creationdate><title>U-Net convolutional neural network-based modification method for precise fabrication of three-dimensional microstructures using laser direct writing lithography</title><author>Sun, Xiuhui ; Yin, Shaoyun ; Jiang, Haibo ; Zhang, Weiguo ; Gao, Mingyou ; Du, Jinglei ; Du, Chunlei</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c320t-d3230082f6b32f6deedff09520a5e5182243045344e15d946cbdd51a0f2a66a53</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Sun, Xiuhui</creatorcontrib><creatorcontrib>Yin, Shaoyun</creatorcontrib><creatorcontrib>Jiang, Haibo</creatorcontrib><creatorcontrib>Zhang, Weiguo</creatorcontrib><creatorcontrib>Gao, Mingyou</creatorcontrib><creatorcontrib>Du, Jinglei</creatorcontrib><creatorcontrib>Du, Chunlei</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>Optics express</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Sun, Xiuhui</au><au>Yin, Shaoyun</au><au>Jiang, Haibo</au><au>Zhang, Weiguo</au><au>Gao, Mingyou</au><au>Du, Jinglei</au><au>Du, Chunlei</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>U-Net convolutional neural network-based modification method for precise fabrication of three-dimensional microstructures using laser direct writing lithography</atitle><jtitle>Optics express</jtitle><addtitle>Opt Express</addtitle><date>2021-02-15</date><risdate>2021</risdate><volume>29</volume><issue>4</issue><spage>6236</spage><epage>6247</epage><pages>6236-6247</pages><issn>1094-4087</issn><eissn>1094-4087</eissn><abstract>In this paper, a modification method based on a U-Net convolutional neural network is proposed for the precise fabrication of three-dimensional microstructures using laser direct writing lithography (LDWL). In order to build the correspondence between the exposure intensity distribution data imported to the laser direct writing system and the surface profile data of the actual fabricated microstructure, these two kinds of data are used as training tensors of the U-Net convolutional neural network, which is proved to be capable of generating their accurate mapping relations. By employing such mapping relations to modify the initial designed exposure intensity data of the parabolic and saddle concave micro-lens with an aperture of 24µm×24µm, it is demonstrated that their fabrication precision, characterized by the mean squared error (MSE) and the peak signal-to-noise ratio (PSNR) between the fabricated and the designed microstructure, can be improved significantly. Specifically, the MSE of the parabolic and saddle concave micro-lens decreased from 100 to 17 and 151 to 50, respectively, and the PSNR increased from 22dB to 29dB and 20dB to 25dB, respectively. Furthermore, the effect of laser beam shaping using these two kinds of micro-lens has also been improved considerably. This study provides a new solution for the fabrication of high-precision three-dimensional microstructures by LDWL.</abstract><cop>United States</cop><pmid>33726149</pmid><doi>10.1364/OE.416871</doi><tpages>12</tpages><orcidid>https://orcid.org/0000-0002-2596-7010</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1094-4087
ispartof Optics express, 2021-02, Vol.29 (4), p.6236-6247
issn 1094-4087
1094-4087
language eng
recordid cdi_proquest_miscellaneous_2502205901
source DOAJ Directory of Open Access Journals; EZB-FREE-00999 freely available EZB journals; Alma/SFX Local Collection
title U-Net convolutional neural network-based modification method for precise fabrication of three-dimensional microstructures using laser direct writing lithography
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-03T22%3A01%3A35IST&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=U-Net%20convolutional%20neural%20network-based%20modification%20method%20for%20precise%20fabrication%20of%20three-dimensional%20microstructures%20using%20laser%20direct%20writing%20lithography&rft.jtitle=Optics%20express&rft.au=Sun,%20Xiuhui&rft.date=2021-02-15&rft.volume=29&rft.issue=4&rft.spage=6236&rft.epage=6247&rft.pages=6236-6247&rft.issn=1094-4087&rft.eissn=1094-4087&rft_id=info:doi/10.1364/OE.416871&rft_dat=%3Cproquest_cross%3E2502205901%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=2502205901&rft_id=info:pmid/33726149&rfr_iscdi=true