A Low-Latency and High-Performance Microwave Photonic AOA and IFM System Based on Deep Learning and FPGA

The angle of arrival (AOA) estimation and instantaneous frequency measurement (IFM) are the important aspects of radar, communication, and electronic warfare, and there is an urgent need to find intelligent solutions that are faster and more accurate than the traditional methods. Currently, deep learning (DL) has increasingly strong learning and feature extraction capabilities, which brings new opportunities to the field of electromagnetic signal processing. However, the models in DL have a large number of parameters, high storage requirements, and long computational latency and not practical for deploying applications on resource-limited devices. In this article, we build a complete AOA and IFM system for the first time, taking advantage of microwave photonics (MWPs) technology, DL, and features of field-programmable gate array (FPGA). Then, a novel hardware-friendly pruning-quantization-iteration compression (PQIC) algorithm is proposed for the post-processing of MWP signal measurement applications. By reducing the data width from 32 bits to four bits, the compressed algorithm reduces parameter storage requirements and hardware implementation complexity with negligible performance loss. Finally, we deploy the acceleration system and test the actual collected signal data on FPGA while running 200 MHz. The results show that with a $14\times $ model compression and a $3.99\times $ reduction in operations, the accuracy of AOA reaches 98.82%, with the mean absolute error (MAE) of 0.27°. More importantly, the running latency is only $20.78~\mu $ s, meeting the real-time processing requirements of MWP signal processing. It is also applicable to real-world signal intelligence processing and demonstrates superior performance compared to other existing algorithms in this field.

I. Introduction

Owing to its wide application in fields, such as radar, wireless communication, electronic warfare, seismic measurement, and autonomous driving [1], [2], [3], [4], electromagnetic signal measurement, including angle of arrival (AOA) estimation and instantaneous frequency measurement (IFM), has always been a hot research topic in the field of electromagnetic signal processing. However, traditional electronic-based methods face challenges in handling large instantaneous bandwidth and electromagnetic interference. To overcome these issues, researchers have turned attention to the application of microwave photonics (MWPs) technology, which offers advantages, such as ultrawideband operation, low cost, and immunity to electromagnetic interference. For example, MWP sensors, combined with deep learning (DL) [5] or machine learning [6], have become one of the feasible solutions to enhance signal processing performance.