Deep Learning Piston Aberration Control of Fiber Laser Phased Array By Spiral Phase Modulation
The stochastic parallel gradient descent (SPGD) algorithm is usually employed as the control strategy for phase-locking in fiber laser phased array systems. However, the convergence speed of the SPGD algorithm will slow down as the number of array elements increases. To improve the control bandwidth...
Gespeichert in:
| Veröffentlicht in: | Journal of lightwave technology 2022-06, Vol.40 (12), p.3980-3991 |
|---|---|
| Hauptverfasser: | , , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 3991 |
|---|---|
| container_issue | 12 |
| container_start_page | 3980 |
| container_title | Journal of lightwave technology |
| container_volume | 40 |
| creator | Zuo, Jing Jia, Haolong Geng, Chao Bao, Qiliang Zou, Fan Li, Ziqiang Jiang, Jing Li, Feng Li, Bincheng Li, Xinyang |
| description | The stochastic parallel gradient descent (SPGD) algorithm is usually employed as the control strategy for phase-locking in fiber laser phased array systems. However, the convergence speed of the SPGD algorithm will slow down as the number of array elements increases. To improve the control bandwidth, the convolutional neural network is introduced to quickly calculate the initial piston aberration in a single step. In addition, the irrationality of the commonly used Mean Square Error (MSE) evaluation function in existing convolutional neural networks is analyzed. A new evaluation function NPCD (Normalized Phase Cosine Distance) is proposed to improve the accuracy of the neural networks. The results show that the piston aberration residual is 0.005 and the normalized power in the bucket (PIB) is 0.993 in the simulation and 0.933 in the experiment after accurate preliminary compensation, which means that the system directly enters the co-phase state. We also demonstrate the robustness and scalability by expanding the scale of the array. |
| doi_str_mv | 10.1109/JLT.2022.3151628 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_crossref_primary_10_1109_JLT_2022_3151628</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9714866</ieee_id><sourcerecordid>2674084062</sourcerecordid><originalsourceid>FETCH-LOGICAL-c291t-44231ec72c073ac4b2cfeecff849ed741d0ce2e41f4a09602effc5f93e545e383</originalsourceid><addsrcrecordid>eNo9kEtPwzAQhC0EEqVwR-JiiXOCX0mcYymUh4KoRLliuc4aUoU42Omh_x6XVFx2VqtvdleD0CUlKaWkvHmuVikjjKWcZjRn8ghNaJbJhDHKj9GEFJwnsmDiFJ2FsCGECiGLCfq4A-hxBdp3TfeJl00YXIdna_BeD01s564bvGuxs3jRxDGudIh1-RWlxrOI7fDtDr_1jdftOMYvrt62f_ZzdGJ1G-DioFP0vrhfzR-T6vXhaT6rEsNKOiRCME7BFMzEP7URa2YsgLFWihLqQtCaGGAgqBWalDlhYK3JbMkhExlwyafoetzbe_ezhTCojdv6Lp5ULC8EkYLkLFJkpIx3IXiwqvfNt_Y7RYnap6hiimqfojqkGC1Xo6UBgH-8LKiQec5_AY9-bbg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2674084062</pqid></control><display><type>article</type><title>Deep Learning Piston Aberration Control of Fiber Laser Phased Array By Spiral Phase Modulation</title><source>IEEE Electronic Library (IEL)</source><creator>Zuo, Jing ; Jia, Haolong ; Geng, Chao ; Bao, Qiliang ; Zou, Fan ; Li, Ziqiang ; Jiang, Jing ; Li, Feng ; Li, Bincheng ; Li, Xinyang</creator><creatorcontrib>Zuo, Jing ; Jia, Haolong ; Geng, Chao ; Bao, Qiliang ; Zou, Fan ; Li, Ziqiang ; Jiang, Jing ; Li, Feng ; Li, Bincheng ; Li, Xinyang</creatorcontrib><description>The stochastic parallel gradient descent (SPGD) algorithm is usually employed as the control strategy for phase-locking in fiber laser phased array systems. However, the convergence speed of the SPGD algorithm will slow down as the number of array elements increases. To improve the control bandwidth, the convolutional neural network is introduced to quickly calculate the initial piston aberration in a single step. In addition, the irrationality of the commonly used Mean Square Error (MSE) evaluation function in existing convolutional neural networks is analyzed. A new evaluation function NPCD (Normalized Phase Cosine Distance) is proposed to improve the accuracy of the neural networks. The results show that the piston aberration residual is 0.005 and the normalized power in the bucket (PIB) is 0.993 in the simulation and 0.933 in the experiment after accurate preliminary compensation, which means that the system directly enters the co-phase state. We also demonstrate the robustness and scalability by expanding the scale of the array.</description><identifier>ISSN: 0733-8724</identifier><identifier>EISSN: 1558-2213</identifier><identifier>DOI: 10.1109/JLT.2022.3151628</identifier><identifier>CODEN: JLTEDG</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Aberration ; Algorithms ; Artificial neural networks ; Convolutional neural network ; Convolutional neural networks ; evaluation func- tion ; fiber laser phased array ; Fiber lasers ; Laser arrays ; Laser beams ; Locking ; Machine learning ; Neural networks ; Phase modulation ; phase-locking ; Phased arrays ; Pistons ; Shape ; Spirals ; Trigonometric functions</subject><ispartof>Journal of lightwave technology, 2022-06, Vol.40 (12), p.3980-3991</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c291t-44231ec72c073ac4b2cfeecff849ed741d0ce2e41f4a09602effc5f93e545e383</citedby><cites>FETCH-LOGICAL-c291t-44231ec72c073ac4b2cfeecff849ed741d0ce2e41f4a09602effc5f93e545e383</cites><orcidid>0000-0002-9711-3452 ; 0000-0003-3873-9743 ; 0000-0002-9166-0455 ; 0000-0002-4471-2865 ; 0000-0001-8287-9597 ; 0000-0002-8685-0924 ; 0000-0001-7243-368X ; 0000-0002-4214-1050</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9714866$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,776,780,792,27901,27902,54733</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9714866$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Zuo, Jing</creatorcontrib><creatorcontrib>Jia, Haolong</creatorcontrib><creatorcontrib>Geng, Chao</creatorcontrib><creatorcontrib>Bao, Qiliang</creatorcontrib><creatorcontrib>Zou, Fan</creatorcontrib><creatorcontrib>Li, Ziqiang</creatorcontrib><creatorcontrib>Jiang, Jing</creatorcontrib><creatorcontrib>Li, Feng</creatorcontrib><creatorcontrib>Li, Bincheng</creatorcontrib><creatorcontrib>Li, Xinyang</creatorcontrib><title>Deep Learning Piston Aberration Control of Fiber Laser Phased Array By Spiral Phase Modulation</title><title>Journal of lightwave technology</title><addtitle>JLT</addtitle><description>The stochastic parallel gradient descent (SPGD) algorithm is usually employed as the control strategy for phase-locking in fiber laser phased array systems. However, the convergence speed of the SPGD algorithm will slow down as the number of array elements increases. To improve the control bandwidth, the convolutional neural network is introduced to quickly calculate the initial piston aberration in a single step. In addition, the irrationality of the commonly used Mean Square Error (MSE) evaluation function in existing convolutional neural networks is analyzed. A new evaluation function NPCD (Normalized Phase Cosine Distance) is proposed to improve the accuracy of the neural networks. The results show that the piston aberration residual is 0.005 and the normalized power in the bucket (PIB) is 0.993 in the simulation and 0.933 in the experiment after accurate preliminary compensation, which means that the system directly enters the co-phase state. We also demonstrate the robustness and scalability by expanding the scale of the array.</description><subject>Aberration</subject><subject>Algorithms</subject><subject>Artificial neural networks</subject><subject>Convolutional neural network</subject><subject>Convolutional neural networks</subject><subject>evaluation func- tion</subject><subject>fiber laser phased array</subject><subject>Fiber lasers</subject><subject>Laser arrays</subject><subject>Laser beams</subject><subject>Locking</subject><subject>Machine learning</subject><subject>Neural networks</subject><subject>Phase modulation</subject><subject>phase-locking</subject><subject>Phased arrays</subject><subject>Pistons</subject><subject>Shape</subject><subject>Spirals</subject><subject>Trigonometric functions</subject><issn>0733-8724</issn><issn>1558-2213</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNo9kEtPwzAQhC0EEqVwR-JiiXOCX0mcYymUh4KoRLliuc4aUoU42Omh_x6XVFx2VqtvdleD0CUlKaWkvHmuVikjjKWcZjRn8ghNaJbJhDHKj9GEFJwnsmDiFJ2FsCGECiGLCfq4A-hxBdp3TfeJl00YXIdna_BeD01s564bvGuxs3jRxDGudIh1-RWlxrOI7fDtDr_1jdftOMYvrt62f_ZzdGJ1G-DioFP0vrhfzR-T6vXhaT6rEsNKOiRCME7BFMzEP7URa2YsgLFWihLqQtCaGGAgqBWalDlhYK3JbMkhExlwyafoetzbe_ezhTCojdv6Lp5ULC8EkYLkLFJkpIx3IXiwqvfNt_Y7RYnap6hiimqfojqkGC1Xo6UBgH-8LKiQec5_AY9-bbg</recordid><startdate>20220615</startdate><enddate>20220615</enddate><creator>Zuo, Jing</creator><creator>Jia, Haolong</creator><creator>Geng, Chao</creator><creator>Bao, Qiliang</creator><creator>Zou, Fan</creator><creator>Li, Ziqiang</creator><creator>Jiang, Jing</creator><creator>Li, Feng</creator><creator>Li, Bincheng</creator><creator>Li, Xinyang</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>7SP</scope><scope>7U5</scope><scope>8FD</scope><scope>H8D</scope><scope>L7M</scope><orcidid>https://orcid.org/0000-0002-9711-3452</orcidid><orcidid>https://orcid.org/0000-0003-3873-9743</orcidid><orcidid>https://orcid.org/0000-0002-9166-0455</orcidid><orcidid>https://orcid.org/0000-0002-4471-2865</orcidid><orcidid>https://orcid.org/0000-0001-8287-9597</orcidid><orcidid>https://orcid.org/0000-0002-8685-0924</orcidid><orcidid>https://orcid.org/0000-0001-7243-368X</orcidid><orcidid>https://orcid.org/0000-0002-4214-1050</orcidid></search><sort><creationdate>20220615</creationdate><title>Deep Learning Piston Aberration Control of Fiber Laser Phased Array By Spiral Phase Modulation</title><author>Zuo, Jing ; Jia, Haolong ; Geng, Chao ; Bao, Qiliang ; Zou, Fan ; Li, Ziqiang ; Jiang, Jing ; Li, Feng ; Li, Bincheng ; Li, Xinyang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c291t-44231ec72c073ac4b2cfeecff849ed741d0ce2e41f4a09602effc5f93e545e383</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Aberration</topic><topic>Algorithms</topic><topic>Artificial neural networks</topic><topic>Convolutional neural network</topic><topic>Convolutional neural networks</topic><topic>evaluation func- tion</topic><topic>fiber laser phased array</topic><topic>Fiber lasers</topic><topic>Laser arrays</topic><topic>Laser beams</topic><topic>Locking</topic><topic>Machine learning</topic><topic>Neural networks</topic><topic>Phase modulation</topic><topic>phase-locking</topic><topic>Phased arrays</topic><topic>Pistons</topic><topic>Shape</topic><topic>Spirals</topic><topic>Trigonometric functions</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zuo, Jing</creatorcontrib><creatorcontrib>Jia, Haolong</creatorcontrib><creatorcontrib>Geng, Chao</creatorcontrib><creatorcontrib>Bao, Qiliang</creatorcontrib><creatorcontrib>Zou, Fan</creatorcontrib><creatorcontrib>Li, Ziqiang</creatorcontrib><creatorcontrib>Jiang, Jing</creatorcontrib><creatorcontrib>Li, Feng</creatorcontrib><creatorcontrib>Li, Bincheng</creatorcontrib><creatorcontrib>Li, Xinyang</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>Electronics & Communications Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>Technology Research Database</collection><collection>Aerospace Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>Journal of lightwave technology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Zuo, Jing</au><au>Jia, Haolong</au><au>Geng, Chao</au><au>Bao, Qiliang</au><au>Zou, Fan</au><au>Li, Ziqiang</au><au>Jiang, Jing</au><au>Li, Feng</au><au>Li, Bincheng</au><au>Li, Xinyang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Deep Learning Piston Aberration Control of Fiber Laser Phased Array By Spiral Phase Modulation</atitle><jtitle>Journal of lightwave technology</jtitle><stitle>JLT</stitle><date>2022-06-15</date><risdate>2022</risdate><volume>40</volume><issue>12</issue><spage>3980</spage><epage>3991</epage><pages>3980-3991</pages><issn>0733-8724</issn><eissn>1558-2213</eissn><coden>JLTEDG</coden><abstract>The stochastic parallel gradient descent (SPGD) algorithm is usually employed as the control strategy for phase-locking in fiber laser phased array systems. However, the convergence speed of the SPGD algorithm will slow down as the number of array elements increases. To improve the control bandwidth, the convolutional neural network is introduced to quickly calculate the initial piston aberration in a single step. In addition, the irrationality of the commonly used Mean Square Error (MSE) evaluation function in existing convolutional neural networks is analyzed. A new evaluation function NPCD (Normalized Phase Cosine Distance) is proposed to improve the accuracy of the neural networks. The results show that the piston aberration residual is 0.005 and the normalized power in the bucket (PIB) is 0.993 in the simulation and 0.933 in the experiment after accurate preliminary compensation, which means that the system directly enters the co-phase state. We also demonstrate the robustness and scalability by expanding the scale of the array.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/JLT.2022.3151628</doi><tpages>12</tpages><orcidid>https://orcid.org/0000-0002-9711-3452</orcidid><orcidid>https://orcid.org/0000-0003-3873-9743</orcidid><orcidid>https://orcid.org/0000-0002-9166-0455</orcidid><orcidid>https://orcid.org/0000-0002-4471-2865</orcidid><orcidid>https://orcid.org/0000-0001-8287-9597</orcidid><orcidid>https://orcid.org/0000-0002-8685-0924</orcidid><orcidid>https://orcid.org/0000-0001-7243-368X</orcidid><orcidid>https://orcid.org/0000-0002-4214-1050</orcidid></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 0733-8724 |
| ispartof | Journal of lightwave technology, 2022-06, Vol.40 (12), p.3980-3991 |
| issn | 0733-8724 1558-2213 |
| language | eng |
| recordid | cdi_crossref_primary_10_1109_JLT_2022_3151628 |
| source | IEEE Electronic Library (IEL) |
| subjects | Aberration Algorithms Artificial neural networks Convolutional neural network Convolutional neural networks evaluation func- tion fiber laser phased array Fiber lasers Laser arrays Laser beams Locking Machine learning Neural networks Phase modulation phase-locking Phased arrays Pistons Shape Spirals Trigonometric functions |
| title | Deep Learning Piston Aberration Control of Fiber Laser Phased Array By Spiral Phase Modulation |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-19T11%3A46%3A16IST&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=Deep%20Learning%20Piston%20Aberration%20Control%20of%20Fiber%20Laser%20Phased%20Array%20By%20Spiral%20Phase%20Modulation&rft.jtitle=Journal%20of%20lightwave%20technology&rft.au=Zuo,%20Jing&rft.date=2022-06-15&rft.volume=40&rft.issue=12&rft.spage=3980&rft.epage=3991&rft.pages=3980-3991&rft.issn=0733-8724&rft.eissn=1558-2213&rft.coden=JLTEDG&rft_id=info:doi/10.1109/JLT.2022.3151628&rft_dat=%3Cproquest_RIE%3E2674084062%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=2674084062&rft_id=info:pmid/&rft_ieee_id=9714866&rfr_iscdi=true |