Document Type

Journal Article

Publication Title

Drones

Volume

7

Issue

7

Publisher

MDPI

School

School of Science

RAS ID

61980

Funders

Special Project on Governmental International Science and Technology Innovation Cooperation / National Key Research and Development Program / National Natural Science Foundation of China

Comments

Liu, X., Song, Y., Chen, K., Yan, S., Chen, S., & Shi, B. (2023). Modulation recognition of low-SNR UAV radar signals based on bispectral slices and GA-BP neural network. Drones, 7(7), article 472. https://doi.org/10.3390/drones7070472

Abstract

In this paper, we address the challenge of low recognition rates in existing methods for radar signals from unmanned aerial vehicles (UAV) with low signal-to-noise ratios (SNRs). To overcome this challenge, we propose the utilization of the bispectral slice approach for accurate recognition of complex UAV radar signals. Our approach involves extracting the bispectral diagonal slice and the maximum bispectral amplitude horizontal slice from the bispectrum amplitude spectrum of the received UAV radar signal. These slices serve as the basis for subsequent identification by calculating characteristic parameters such as convexity, box dimension, and sparseness. To accomplish the recognition task, we employ a GA-BP neural network. The significant variations observed in the bispectral slices of different signals, along with their robustness against Gaussian noise, contribute to the high separability and stability of the extracted bispectral convexity, bispectral box dimension, and bispectral sparseness. Through simulations involving five radar signals, our proposed method demonstrates superior performance. Remarkably, even under challenging conditions with an SNR as low as −3 dB, the recognition accuracy for the five different radar signals exceeds 90%. Our research aims to enhance the understanding and application of modulation recognition techniques for UAV radar signals, particularly in scenarios with low SNRs.

DOI

10.3390/drones7070472

Creative Commons License

Creative Commons Attribution 4.0 License
This work is licensed under a Creative Commons Attribution 4.0 License.

Download

Share

 
COinS