A Planar Array Synthesis Method Based on Deep Learning and Radiation Pattern Superposition Method

A dual-branched convolutional neural network (CNN) integrated with hybrid training criteria is proposed for real-time multibeam synthesis in planar uniform antenna arrays. For higher speed in dataset generation, the pattern superposition method is introduced in this article, which significantly impr...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on antennas and propagation Ročník 73; číslo 8; s. 5265 - 5277
Hlavní autoři:	Huang, Jianming, Liu, Rui, Zhang, Naibo, Cui, Yansong, Ren, Weizheng, Guo, Qiuquan, Du, Yanjun, Zhao, Jiayu
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 01.08.2025 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Antenna arrays Antenna design Antenna radiation patterns Antennas Approximation Arrays Artificial neural networks Beam steering Beamforming convolutional networks Convolutional neural networks Criteria Deep learning Machine learning Neural networks Optimization Planar arrays Real time Real-time systems Reconfiguration Sidelobe reduction Sidelobes Stochastic processes Synthesis Training
ISSN:	0018-926X, 1558-2221
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	A dual-branched convolutional neural network (CNN) integrated with hybrid training criteria is proposed for real-time multibeam synthesis in planar uniform antenna arrays. For higher speed in dataset generation, the pattern superposition method is introduced in this article, which significantly improves data generation speed (~0.7 ms per each). With a new hybrid training strategy integrating both "data-driven approximation" and "physics-informed approximation" criteria, flexible training while maintaining model synthesis efficiency is achieved simultaneously. Based on the approaches mentioned above, the proposed dual-branched CNN enables a dynamic multiobjective balance between its two branch outputs, accomplishing amplitude-phase synthesis for antenna array design. In the numerical simulation, consistent sidelobe suppression (<inline-formula> <tex-math notation="LaTeX">20\sim 40 </tex-math></inline-formula> dB) is demonstrated for dual-beam steering across <inline-formula> <tex-math notation="LaTeX">10^{\circ }{\sim }20^{\circ } </tex-math></inline-formula> off-axis angles, with high synthesis speeds (~0.05 s per each) on suitable computing platforms. In comparison experiments, the proposed method outperforms typical population-based stochastic optimization algorithms and deep neuron network (DNN) structure in both synthesis efficiency and pattern regularity. The model's real-time capability is verified for beam reconfiguration scenarios requiring subsecond responses, suggesting a new pathway for physics-embedded deep learning in antenna array synthesis.
AbstractList	A dual-branched convolutional neural network (CNN) integrated with hybrid training criteria is proposed for real-time multibeam synthesis in planar uniform antenna arrays. For higher speed in dataset generation, the pattern superposition method is introduced in this article, which significantly improves data generation speed (~0.7 ms per each). With a new hybrid training strategy integrating both “data-driven approximation” and “physics-informed approximation” criteria, flexible training while maintaining model synthesis efficiency is achieved simultaneously. Based on the approaches mentioned above, the proposed dual-branched CNN enables a dynamic multiobjective balance between its two branch outputs, accomplishing amplitude-phase synthesis for antenna array design. In the numerical simulation, consistent sidelobe suppression ([Formula Omitted] dB) is demonstrated for dual-beam steering across [Formula Omitted] off-axis angles, with high synthesis speeds (~0.05 s per each) on suitable computing platforms. In comparison experiments, the proposed method outperforms typical population-based stochastic optimization algorithms and deep neuron network (DNN) structure in both synthesis efficiency and pattern regularity. The model’s real-time capability is verified for beam reconfiguration scenarios requiring subsecond responses, suggesting a new pathway for physics-embedded deep learning in antenna array synthesis. A dual-branched convolutional neural network (CNN) integrated with hybrid training criteria is proposed for real-time multibeam synthesis in planar uniform antenna arrays. For higher speed in dataset generation, the pattern superposition method is introduced in this article, which significantly improves data generation speed (~0.7 ms per each). With a new hybrid training strategy integrating both "data-driven approximation" and "physics-informed approximation" criteria, flexible training while maintaining model synthesis efficiency is achieved simultaneously. Based on the approaches mentioned above, the proposed dual-branched CNN enables a dynamic multiobjective balance between its two branch outputs, accomplishing amplitude-phase synthesis for antenna array design. In the numerical simulation, consistent sidelobe suppression (<inline-formula> <tex-math notation="LaTeX">20\sim 40 </tex-math></inline-formula> dB) is demonstrated for dual-beam steering across <inline-formula> <tex-math notation="LaTeX">10^{\circ }{\sim }20^{\circ } </tex-math></inline-formula> off-axis angles, with high synthesis speeds (~0.05 s per each) on suitable computing platforms. In comparison experiments, the proposed method outperforms typical population-based stochastic optimization algorithms and deep neuron network (DNN) structure in both synthesis efficiency and pattern regularity. The model's real-time capability is verified for beam reconfiguration scenarios requiring subsecond responses, suggesting a new pathway for physics-embedded deep learning in antenna array synthesis.
Author	Liu, Rui Cui, Yansong Zhao, Jiayu Zhang, Naibo Ren, Weizheng Huang, Jianming Guo, Qiuquan Du, Yanjun
Author_xml	– sequence: 1 givenname: Jianming orcidid: 0009-0008-0392-1477 surname: Huang fullname: Huang, Jianming organization: School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China – sequence: 2 givenname: Rui orcidid: 0009-0006-0771-1739 surname: Liu fullname: Liu, Rui organization: School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China – sequence: 3 givenname: Naibo orcidid: 0000-0003-1017-1033 surname: Zhang fullname: Zhang, Naibo email: zhangnaibai@163.com organization: School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China – sequence: 4 givenname: Yansong surname: Cui fullname: Cui, Yansong organization: School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China – sequence: 5 givenname: Weizheng orcidid: 0000-0002-3509-8488 surname: Ren fullname: Ren, Weizheng organization: School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China – sequence: 6 givenname: Qiuquan surname: Guo fullname: Guo, Qiuquan organization: Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China – sequence: 7 givenname: Yanjun orcidid: 0009-0008-2024-9133 surname: Du fullname: Du, Yanjun organization: School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China – sequence: 8 givenname: Jiayu surname: Zhao fullname: Zhao, Jiayu email: ejmhuang@bupt.edu.cn organization: School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China
BookMark	eNpNkL1PwzAQxS1UJNrCzsBgiTnF307GUD6lIipaJDbLTi40VXGCnQ7970kJA9Pp7t57p_tN0Mg3HhC6pGRGKclu1vlyxgiTMy6V0ESeoDGVMk0YY3SExoTQNMmY-jhDkxi3fStSIcbI5ni5s94GnIdgD3h18N0GYh3xC3SbpsS3NkKJG4_vAFq8ABt87T-x9SV-s2Vtu7rfLW3XQfB4tW8htE2sf6dDwjk6rewuwsVfnaL3h_v1_ClZvD4-z_NFUjChu0RpXfR_EMWEs1a5wjFCeepcKW3pOFOFtlpLXhRO6lRVSlTCpbwkWcWBOuBTdD3ktqH53kPszLbZB9-fNJwJxSVhQvYqMqiK0MQYoDJtqL9sOBhKzBGk6UGaI0jzB7K3XA2WGgD-ybOUCa75D0EXcMc
CODEN	IETPAK
Cites_doi	10.1109/LAWP.2013.2270930 10.1109/TAP.2023.3278878 10.1109/TAP.2021.3069467 10.1109/TKDE.2009.191 10.1109/TNNLS.2019.2927869 10.1109/APUSNCURSINRSM.2019.8888573 10.1109/TAP.2011.2173111 10.1109/compem.2018.8496657 10.1109/CVPR.2016.90 10.1038/nature14539 10.1016/0893-6080(91)90009-T 10.1109/JRPROC.1946.225956 10.1109/ACCESS.2023.3317371 10.1002/ett.4754 10.1109/MSP.2012.2205597 10.1002/mmce.22356 10.1109/TAI.2022.3192505 10.3311/PPee.22111 10.1002/mmce.23442 10.1109/csqrwc.2018.8454981 10.1109/TAP.2010.2048864 10.1109/TIE.2020.3001849 10.1145/3065386 10.1109/LWC.2018.2832128 10.1002/mop.10128 10.1109/TAP.2018.2871712 10.1109/TAP.2022.3140214 10.1109/LAWP.2017.2714182 10.1016/j.aeue.2012.03.012 10.1109/TAP.2007.910490 10.1109/JETCAS.2020.2972764 10.1049/ji-3-2.1948.0094 10.1016/j.aeue.2023.154788
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
DBID	97E RIA RIE AAYXX CITATION 7SP 8FD L7M
DOI	10.1109/TAP.2025.3564705
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEL CrossRef Electronics & Communications Abstracts Technology Research Database Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts
DatabaseTitleList	Technology Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEL url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1558-2221
EndPage	5277
ExternalDocumentID	10_1109_TAP_2025_3564705 10982437
Genre	orig-research
GroupedDBID	-~X 0R~ 29I 4.4 5GY 5VS 6IK 85S 97E AAJGR AASAJ AAWTH ABAZT ABFSI ABQJQ ABVLG ACGFO ACGFS ACIWK ACKIV ACNCT AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 E.L EBS EJD F5P HZ~ H~9 IAAWW IBMZZ ICLAB IDIHD IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS RXW TAE TAF TN5 VH1 VJK VOH AAYXX CITATION 7SP 8FD AARMG L7M
ID	FETCH-LOGICAL-c247t-677c1090624baa6bcb20138bbd5adb326c7a7753ccb5786f64f4b83d09f3e1be3
IEDL.DBID	RIE
ISICitedReferencesCount	0
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001547923100005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0018-926X
IngestDate	Fri Sep 12 20:12:23 EDT 2025 Sat Nov 29 06:57:17 EST 2025 Sun Sep 28 03:48:01 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	8
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c247t-677c1090624baa6bcb20138bbd5adb326c7a7753ccb5786f64f4b83d09f3e1be3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0009-0008-2024-9133 0009-0006-0771-1739 0009-0008-0392-1477 0000-0002-3509-8488 0000-0003-1017-1033
PQID	3246350245
PQPubID	85476
PageCount	13
ParticipantIDs	proquest_journals_3246350245 ieee_primary_10982437 crossref_primary_10_1109_TAP_2025_3564705
PublicationCentury	2000
PublicationDate	2025-08-01
PublicationDateYYYYMMDD	2025-08-01
PublicationDate_xml	– month: 08 year: 2025 text: 2025-08-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on antennas and propagation
PublicationTitleAbbrev	TAP
PublicationYear	2025
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref35 ref12 Kingma (ref40) 2014 ref15 ref37 ref14 ref31 ref30 ref11 ref33 ref32 ref2 ref1 ref17 ref39 ref16 ref38 ref19 ref18 Aljaf (ref24) 2023; 18 Simonyan (ref34) 2014 Bengio (ref36) 2017 ref23 ref26 ref25 ref20 ref22 ref21 Tompson (ref4); 27 Balanis (ref10) 2016 ref28 ref27 ref29 ref8 ref9 ref3 ref6 ref5 Tompson (ref7)
References_xml	– ident: ref22 doi: 10.1109/LAWP.2013.2270930 – ident: ref16 doi: 10.1109/TAP.2023.3278878 – volume: 18 start-page: 1199 issue: 2 year: 2023 ident: ref24 article-title: Multiple array patterns reconfiguration with common excitation amplitudes and optimized phases publication-title: J. Eng. Sci. Technol. – ident: ref28 doi: 10.1109/TAP.2021.3069467 – ident: ref39 doi: 10.1109/TKDE.2009.191 – ident: ref2 doi: 10.1109/TNNLS.2019.2927869 – ident: ref31 doi: 10.1109/APUSNCURSINRSM.2019.8888573 – ident: ref17 doi: 10.1109/TAP.2011.2173111 – ident: ref8 doi: 10.1109/compem.2018.8496657 – ident: ref38 doi: 10.1109/CVPR.2016.90 – year: 2014 ident: ref40 article-title: Adam: A method for stochastic optimization publication-title: arXiv:1412.6980 – ident: ref6 doi: 10.1038/nature14539 – ident: ref35 doi: 10.1016/0893-6080(91)90009-T – ident: ref11 doi: 10.1109/JRPROC.1946.225956 – ident: ref27 doi: 10.1109/ACCESS.2023.3317371 – ident: ref14 doi: 10.1002/ett.4754 – ident: ref5 doi: 10.1109/MSP.2012.2205597 – volume-title: Antenna Theory: Analysis and Design year: 2016 ident: ref10 – ident: ref25 doi: 10.1002/mmce.22356 – volume: 27 start-page: 1799 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref4 article-title: Joint training of a convolutional network and a graphical model for human pose estimation – ident: ref30 doi: 10.1109/TAI.2022.3192505 – ident: ref23 doi: 10.3311/PPee.22111 – year: 2014 ident: ref34 article-title: Very deep convolutional networks for large-scale image recognition publication-title: arXiv:1409.1556 – ident: ref13 doi: 10.1002/mmce.23442 – ident: ref32 doi: 10.1109/csqrwc.2018.8454981 – ident: ref21 doi: 10.1109/TAP.2010.2048864 – ident: ref3 doi: 10.1109/TIE.2020.3001849 – ident: ref1 doi: 10.1145/3065386 – ident: ref9 doi: 10.1109/LWC.2018.2832128 – ident: ref18 doi: 10.1002/mop.10128 – ident: ref37 doi: 10.1109/TAP.2018.2871712 – ident: ref29 doi: 10.1109/TAP.2022.3140214 – volume-title: Deep Learning year: 2017 ident: ref36 – ident: ref20 doi: 10.1109/LAWP.2017.2714182 – ident: ref26 doi: 10.1016/j.aeue.2012.03.012 – ident: ref19 doi: 10.1109/TAP.2007.910490 – ident: ref33 doi: 10.1109/JETCAS.2020.2972764 – ident: ref12 doi: 10.1049/ji-3-2.1948.0094 – start-page: 3424 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref7 article-title: Accelerating Eulerian fluid simulation with convolutional networks – ident: ref15 doi: 10.1016/j.aeue.2023.154788
SSID	ssj0014844
Score	2.4753985
Snippet	A dual-branched convolutional neural network (CNN) integrated with hybrid training criteria is proposed for real-time multibeam synthesis in planar uniform...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Index Database Publisher
StartPage	5265
SubjectTerms	Antenna arrays Antenna design Antenna radiation patterns Antennas Approximation Arrays Artificial neural networks Beam steering Beamforming convolutional networks Convolutional neural networks Criteria Deep learning Machine learning Neural networks Optimization Planar arrays Real time Real-time systems Reconfiguration Sidelobe reduction Sidelobes Stochastic processes Synthesis Training
Title	A Planar Array Synthesis Method Based on Deep Learning and Radiation Pattern Superposition Method
URI	https://ieeexplore.ieee.org/document/10982437 https://www.proquest.com/docview/3246350245
Volume	73
WOSCitedRecordID	wos001547923100005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEL customDbUrl: eissn: 1558-2221 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014844 issn: 0018-926X databaseCode: RIE dateStart: 19630101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8JAEJ4I8aAHnxhRNHvw4qEI7XZ3e8QH8aCECBpuzb5quBRCwYR_7-y2GBLjwVsP202z0-k305n5PoCbSHVliLAQGISrgDLNAgThLLBc0oRrYxPPwPfxwgcDMZkkw2pY3c_CWGt985ltu0tfyzczvXK_ytDDE-EI9GpQ45yVw1o_JQMqaEm53EUPDtlkU5PsJHfj3hAzwTBuRzGj3CnVbWGQF1X59SX28NI__OeDHcFBFUeSXmn4Y9ix-Qnsb7ELnoLsESdJJBe4aiHXZLTOMdorpgV59bLR5B4RzJBZTh6tnZOKafWTyNyQN0dZ4GxGhp6AMyej1dwJcpUtXtUODXjvP40fnoNKUSHQIeXLgHGuXScmC6mSkimtQlepVMrE0iiM5DSXHBMYrRV6MssYzagSkekkWWS7ykZnUM9nuT0HooXBYEljAiQQCJUQmYmsYkqEWRxKTptwuznjdF4SZ6Q-4egkKdojdfZIK3s0oeHOdGtdeZxNaG2sklauVaQYAWKQ5CrGF3_cdgl7bveyTa8F9eViZa9gV38tp8Xi2r8138Vkv4c
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8JAEJ74StSDT4z43IMXD0Vol93tER9EIxIiaLg1-6rxUggFE_69s9tiSIwHbz1sH9np9JvpzHwfwFWkGjJEWAgMwlVAmWYBgnAaWC5pzLWxsWfge-_wblcMh3GvHFb3szDWWt98Zmvu0NfyzUjP3K8y9PBYOAK9VVh30lnluNZP0YAKWpAuN9CHQzZcVCXr8c2g1cNcMGzWoiaj3GnVLaGQl1X59S32ANPe_eej7cFOGUmSVmH6fVix2QFsL_ELHoJsESdKJCe4aiLnpD_PMN7LP3Py4oWjyS1imCGjjNxbOyYl1-oHkZkhr460wFmN9DwFZ0b6s7GT5CqavMorVOCt_TC4ewxKTYVAh5RPA8a5dr2YLKRKSqa0Cl2tUinTlEZhLKe55JjCaK3Ql1nKaEqViEw9TiPbUDY6grVslNljIFoYDJc0pkACoVAJkZrIKqZEmDZDyWkVrhd7nIwL6ozEpxz1OEF7JM4eSWmPKlTcni6tK7azCmcLqySlc-UJxoAYJrma8ckfp13C5uPgpZN0nrrPp7Dl7lQ07Z3B2nQys-ewob-mn_nkwr9B3-w_wtA
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+Planar+Array+Synthesis+Method+Based+on+Deep+Learning+and+Radiation+Pattern+Superposition+Method&rft.jtitle=IEEE+transactions+on+antennas+and+propagation&rft.au=Huang%2C+Jianming&rft.au=Liu%2C+Rui&rft.au=Zhang%2C+Naibo&rft.au=Cui%2C+Yansong&rft.date=2025-08-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=0018-926X&rft.eissn=1558-2221&rft.volume=73&rft.issue=9&rft.spage=5265&rft.epage=5277&rft_id=info:doi/10.1109%2FTAP.2025.3564705&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-926X&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-926X&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-926X&client=summon