Wideband Machine-Learning-Based Amplitude-Only Direction Finding With Spiral Antennas

被引：2

作者：

Friedrichs, Gaeron R. ^{[1
]}

Elmansouri, Mohamed A. ^{[1
]}

Filipovic, Dejan S. ^{[1
]}

机构：

[1] Univ Colorado, Antenna Res Grp, Boulder, CO 80309 USA

来源：

IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION | 2023年 / 71卷 / 12期

基金：

美国国家科学基金会;

关键词：

Direction finding (DF); neural networks (NNs); signal processing; spiral antenna; SIMULTANEOUS TRANSMIT;

D O I：

10.1109/TAP.2023.3326918

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

A method for performing amplitude-only direction finding (DF) with a multiarm spiral antenna is demonstrated over multioctave (1.5-6 GHz) bandwidth, with 360(degrees) coverage in azimuth and 100(degrees) total coverage in elevation. A combined frequency model and compact neural network (NN) architecture are deployed to perform DF in both azimuth and elevation. Root mean square error (RMSE) of about 5(degrees) at 40 dB signal-to-noise ratio (SNR) is demonstrated in measurement for a single-snapshot, machine-learning-based DF system, across two octaves of bandwidth. The wideband system is deployed with no RF beamforming or phase compensation hardware. A multichannel receiver is designed, manufactured, and integrated with an additively manufactured, cavity-backed spiral. An average RMSE of less than 2.5(degrees) is achieved in experiment with cascaded calibration and maintaining at least 30 dB SNR, while obtaining nearly 90% reduction in (digital) system footprint.

引用

页码：9601 / 9609

页数：9