E.V. Kalyabin1, A.V. Prosvirov2, T.A. Mirtalibov3

1,2 JSC “CNIRTI named after academician A.I. Berg” (Moscow, Russia)

3 “Almaz-Antey” Corp. (Moscow, Russia)

1,2 post@cnirti.ru; 3 info@npo-rit.ru

Problem statement. The use of advanced developments in cognitive electronic warfare (EW) makes it possible to achieve a dominant position in the use of the electromagnetic spectrum (EMC). The combination of artificial intelligence and machine learning technologies with advanced electronic warfare (EW) technologies makes it possible to successfully solve the problems of detecting radar pulses of probing signals and determining their modulation. It seems possible to consider a comprehensive system for detecting and classifying radar pulses in an automatic mode for use in CRB equipment. At the input, we have the raw signal of the enemy's radar system (radar) and at the output we receive a fully classified signal according to several parameters. To obtain such information, the short-term Fourier transform is used to obtain a time-frequency image of the signal, the Hough transform, to detect pulses in time-frequency images, and the pulses are represented by a single line. Convolutional neural networks are used to classify impulses. The research presents the results of the classification of modulations at different levels of the useful signal-to-noise ratio.

Goal. The purpose of the article is to show how the interception and classification of radar signals by intra-pulse modulation is carried out to identify the type of enemy radar and further select responses.

Results. It is shown that the determination of the probing signal and its classification according to the type of modulation is possible with different values of the ratio of the useful signal to noise.

Practical significance. The article confirms that the use of neural networks makes it possible to create an algorithm based on a complete scenario for detecting a signal pulse and classifying it in real time.

Kalyabin E.V., Prosvirov A.V., Mirtalibov T.A. Detection of radar pulses of probing signals and determination of their modulation in cognitive electronic warfare systems. Radiotekhnika. 2025. V. 89. № 10. P. 95−102. DOI: https://doi.org/10.18127/j00338486-202510-11 (In Russian)

1. Andreev G.I., Tihomirov V.A., Zamarin M.E. Problemy iskusstvennogo intellekta v tehnicheskoj oblasti radiojelektronnoj bor'by. Radiotehnika. 2024. T. 88 № 5. S. 5-14. DOI: https://doi.org/10.18127/j00338486-202405-01 (in Russian).
2. Geroleo F.G., Brandt-Pearce M. Detection and estimation of LFMCW-radar signals. IEEE Transactions on Aerospace and Electronic Systems. Jan. 2012. V. 48. № 1. Р. 405–418.
3. Lopez-Risueno G., Grajal J., Yeste-Ojeda O. Atomic decomposition-based radar complex signal interception. IEE Proceedings “Radar, Sonar and Navigation”. Aug. 2003. V. 150. № 4. Р. 323.
4. Lopez-Risueno G., Grajal J. Unknown signal detection via atomic decomposition. Proceedings of the 11th IEEE Signal Processing Workshop on Statistical Signal Processing (Cat. No.01TH8563). Aug. 2001. Р. 174–177.
5. Lopez-Risueno G., Grajal J. Multiple signal detection and estimation using atomic decomposition and EM. IEEE Transactions on Aerospace and Electronic Systems. Jan. 2006. V. 42. № 1. Р. 84–102.
6. Jie S., Xiao-ming T., You H. Muti-channel digital LPI signal detector. 2006 CIE International Conference on Radar. Oct. 2006.
   Р. 1–4.
7. Osnovy proektirovanija sredstv radiojelektronnoj bor'by. Pod red. G.I. Andreeva. M.: Radiotehnika. 2024. 348 s. (in Russian).