Improved fully-connected neural network approach for decoupling microstrip antenna array design

Wen-Ying Zhou, Zhong-Lei Mei, Mai Lu and Ya-Bo Zhu

Journal of Electromagnetic Waves and Applications, 2022, vol. 36, issue 14, 1996-2009

Abstract: This article presents an improved fully-connected neural network (FCNN) approach to design a decoupling microstrip antenna array. Through combing the advantage of waveguide (WG) structure and complementary double split ring resonator (CDSRRs), a novel decoupling structure is proposed, which can effectively suppress the mutual coupling between two close patches, and our improved FCNN can predict the geometry of the proposed antenna array to obtain the desired isolation. To demonstrate the validity and reliability of this method, the improved FCNN approach is used to predict the geometric parameters of the proposed antenna array when the distance of patch is reduced to 8 mm, 7mm and 6 mm. The measurement results of the predicted antenna arrays show that, their corresponding isolations are 51.16 dB, 41.99 dB and 42.43 dB respectively. The improved FCNN approach is proved to obtain the optimal isolation with lower computational complexity.

Date: 2022
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/09205071.2022.2051756 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:tewaxx:v:36:y:2022:i:14:p:1996-2009

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/tewa20

DOI: 10.1080/09205071.2022.2051756

Access Statistics for this article

Journal of Electromagnetic Waves and Applications is currently edited by Mohamad Abou El-Nasr and Pankaj Kumar Choudhury

More articles in Journal of Electromagnetic Waves and Applications from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().