基于Xilinx Sx475T的实时5.7-5.8 GHz 32波束近似离散傅立叶变换频谱传感器

IF 5.2 1区 工程技术 Q1 ENGINEERING, ELECTRICAL & ELECTRONIC
Arjuna Madanayake;Umesha Kumarasiri;Sivakumar Sivasankar;Keththura Lawrance;Buddhipriya Gayanath;Hiruni Silva;Soumyajit Mandal;Renato J. Cintra
{"title":"基于Xilinx Sx475T的实时5.7-5.8 GHz 32波束近似离散傅立叶变换频谱传感器","authors":"Arjuna Madanayake;Umesha Kumarasiri;Sivakumar Sivasankar;Keththura Lawrance;Buddhipriya Gayanath;Hiruni Silva;Soumyajit Mandal;Renato J. Cintra","doi":"10.1109/TCSI.2025.3554078","DOIUrl":null,"url":null,"abstract":"The radio spectrum in the sub-6 GHz (FR1) band is crowded and contested, and is sought after by commercial, scientific and defense users. Situational awareness through spectrum sensing, and AI/ML-enabled perception that recognizes behaviors, patterns, modulations, devices and waveforms is a crucial need for emerging autonomous/cognitive radio systems. This work describes measurable progress in the use of extremely low complexity approximate DFT algorithms as multi-beam beamformers in the digital domain for multibeam spatial RF beamforming. The paper begins with a longterm vision for intelligent spectrum awareness across wide bands and multi-directions with multi-chiplet system in package hardware acceleration of both beamforming, Fourier and AI/ML algorithms, followed by a focus account of specific progress with digital architectures and real-time prototype implementations across the 5.7–5.8 GHz band for 32 RF beams. A real-time temporal frequency resolution of 100 kHz across 100 MHz of baseband bandwidth is achieved, across 32 simultaneous fully-digital RF-beams, using a Xilinx Sx475 FPGA implementation. Details of multiplierless approximate DFT beamformers, automated modulation recognition algorithms using AI/ML, analog channelization, spectrum sensing and perception architectures are also discussed. Over-the-air experiments using the RadioML.2018.a dataset confirmed both single source accuracy (better than 97%) and impact of multi-beams on AI/ML performance for multiple strong RFI sources.","PeriodicalId":13039,"journal":{"name":"IEEE Transactions on Circuits and Systems I: Regular Papers","volume":"72 8","pages":"3777-3790"},"PeriodicalIF":5.2000,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Real-Time 5.7–5.8 GHz 32-Beam Approximate Discrete Fourier Transform Spectrum Sensor for RF Perception on Xilinx Sx475T\",\"authors\":\"Arjuna Madanayake;Umesha Kumarasiri;Sivakumar Sivasankar;Keththura Lawrance;Buddhipriya Gayanath;Hiruni Silva;Soumyajit Mandal;Renato J. Cintra\",\"doi\":\"10.1109/TCSI.2025.3554078\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The radio spectrum in the sub-6 GHz (FR1) band is crowded and contested, and is sought after by commercial, scientific and defense users. Situational awareness through spectrum sensing, and AI/ML-enabled perception that recognizes behaviors, patterns, modulations, devices and waveforms is a crucial need for emerging autonomous/cognitive radio systems. This work describes measurable progress in the use of extremely low complexity approximate DFT algorithms as multi-beam beamformers in the digital domain for multibeam spatial RF beamforming. The paper begins with a longterm vision for intelligent spectrum awareness across wide bands and multi-directions with multi-chiplet system in package hardware acceleration of both beamforming, Fourier and AI/ML algorithms, followed by a focus account of specific progress with digital architectures and real-time prototype implementations across the 5.7–5.8 GHz band for 32 RF beams. A real-time temporal frequency resolution of 100 kHz across 100 MHz of baseband bandwidth is achieved, across 32 simultaneous fully-digital RF-beams, using a Xilinx Sx475 FPGA implementation. Details of multiplierless approximate DFT beamformers, automated modulation recognition algorithms using AI/ML, analog channelization, spectrum sensing and perception architectures are also discussed. Over-the-air experiments using the RadioML.2018.a dataset confirmed both single source accuracy (better than 97%) and impact of multi-beams on AI/ML performance for multiple strong RFI sources.\",\"PeriodicalId\":13039,\"journal\":{\"name\":\"IEEE Transactions on Circuits and Systems I: Regular Papers\",\"volume\":\"72 8\",\"pages\":\"3777-3790\"},\"PeriodicalIF\":5.2000,\"publicationDate\":\"2025-04-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Transactions on Circuits and Systems I: Regular Papers\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10947127/\",\"RegionNum\":1,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Circuits and Systems I: Regular Papers","FirstCategoryId":"5","ListUrlMain":"https://ieeexplore.ieee.org/document/10947127/","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0

摘要

sub- 6ghz (FR1)频段的无线电频谱拥挤且竞争激烈,受到商业、科学和国防用户的追捧。通过频谱传感的态势感知,以及识别行为、模式、调制、设备和波形的AI/ ml感知,是新兴自主/认知无线电系统的关键需求。这项工作描述了在数字领域使用极低复杂度的近似DFT算法作为多波束形成器用于多波束空间射频波束形成方面的可测量进展。本文首先提出了在波束形成、傅立叶和AI/ML算法的封装硬件加速中使用多芯片系统实现宽带和多方向智能频谱感知的长期愿景,然后重点介绍了在5.7-5.8 GHz频段上实现32 RF波束的数字架构和实时原型实现的具体进展。使用Xilinx Sx475 FPGA实现,在100 MHz基带带宽上实现了32个同时全数字rf波束的100 kHz实时时间频率分辨率。本文还讨论了无乘法器近似DFT波束形成、使用AI/ML的自动调制识别算法、模拟信道化、频谱传感和感知架构的细节。使用RadioML.2018进行无线实验。数据集证实了单源精度(优于97%)和多波束对多个强RFI源的AI/ML性能的影响。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Real-Time 5.7–5.8 GHz 32-Beam Approximate Discrete Fourier Transform Spectrum Sensor for RF Perception on Xilinx Sx475T
The radio spectrum in the sub-6 GHz (FR1) band is crowded and contested, and is sought after by commercial, scientific and defense users. Situational awareness through spectrum sensing, and AI/ML-enabled perception that recognizes behaviors, patterns, modulations, devices and waveforms is a crucial need for emerging autonomous/cognitive radio systems. This work describes measurable progress in the use of extremely low complexity approximate DFT algorithms as multi-beam beamformers in the digital domain for multibeam spatial RF beamforming. The paper begins with a longterm vision for intelligent spectrum awareness across wide bands and multi-directions with multi-chiplet system in package hardware acceleration of both beamforming, Fourier and AI/ML algorithms, followed by a focus account of specific progress with digital architectures and real-time prototype implementations across the 5.7–5.8 GHz band for 32 RF beams. A real-time temporal frequency resolution of 100 kHz across 100 MHz of baseband bandwidth is achieved, across 32 simultaneous fully-digital RF-beams, using a Xilinx Sx475 FPGA implementation. Details of multiplierless approximate DFT beamformers, automated modulation recognition algorithms using AI/ML, analog channelization, spectrum sensing and perception architectures are also discussed. Over-the-air experiments using the RadioML.2018.a dataset confirmed both single source accuracy (better than 97%) and impact of multi-beams on AI/ML performance for multiple strong RFI sources.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
IEEE Transactions on Circuits and Systems I: Regular Papers
IEEE Transactions on Circuits and Systems I: Regular Papers 工程技术-工程:电子与电气
CiteScore
9.80
自引率
11.80%
发文量
441
审稿时长
2 months
期刊介绍: TCAS I publishes regular papers in the field specified by the theory, analysis, design, and practical implementations of circuits, and the application of circuit techniques to systems and to signal processing. Included is the whole spectrum from basic scientific theory to industrial applications. The field of interest covered includes: - Circuits: Analog, Digital and Mixed Signal Circuits and Systems - Nonlinear Circuits and Systems, Integrated Sensors, MEMS and Systems on Chip, Nanoscale Circuits and Systems, Optoelectronic - Circuits and Systems, Power Electronics and Systems - Software for Analog-and-Logic Circuits and Systems - Control aspects of Circuits and Systems.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信