26-32

UDC 621.396.677.3
DOI: 10.15350/2306-2819.2017.4.26

SPATIAL FILTERING OF IONOSPHERIC MODES IN AN ADAPTIVE ANTENNA BASED ON NEURAL NETWORK TECHNOLOGIES

A. R. Nasybullin, D. A. Vedenkin
Volga State University of Technology,
3, Lenin Square, Yoshkar-Ola, 424000, Russian Federation
E-mail: aydar.nasybullin@mail.ru; denis_ved@mail.ru

ABSTRACT

Introduction. At present the ionosphere state monitoring is a priority direction in science and engineering. The development of radiophysical ionospheric sounding techniques allows getting unique information for researchers in various fields. For example, ionograms determine different characteristics of the atmosphere and radio-frequency transmission channels. Oblique radio sounding methods are of special relevance in the technique of diagnostics and prediction of inospheric layers. One of the problems of that kind of sounding is the necessity of dividing spatial modes with different angles of incidence. The purpose of the work was to consider neural networks algorithms with regard to the problems of the spatial filtering of ionospheric modes in an adaptive linear antenna array. In the process of the development of algorithms of the separation of angles of beams arrival, processing techniques based on the correlation matrix of noisy signals and methods of radial basis neural networks training have been used. Results. The concept of neural networks for determining the angle of arrival of beams consists in training the neural network to determine the presence of signals, received from different directions, automatically. Elements of the input multidimensional vector of the neural network are either signals of antenna array elements or the result of input signals processing. The output vector includes the information about the spatial distribution of ionospheric modes. The training sample consists of a discrete set of possible variants of beams arrival. As a result of training the neural network makes the approximation of the function of many variables and allows determining the angles of arrival, which are not present in the training sample. Conclusion. The algorithm of neural network formation based on a zero error procedure for determining the angles of arrival of two beams is offered. Optimal values of the parameter SPREAD are revealed in the view of reducing the average squared error of the restoration of the angles of beams arrival. Practical significance. The considered ideas can be used further for improving the characteristics of adaptive antenna systems for the ionosphere radio monitoring based on LFM sounding signals.

KEYWORDS

adaptive array antenna; neural network; selection of ionospheric modes; ionosphere diagnostics.

FULL TEXT (pdf)

ACKNOWLEDGMENT

The work was carried out with the financial support from the Russian Science Foundation (Grant №15-19-10053).

REFERENCES

1. Ratynsky M.V. Adaptatsiya i sverkhrazreshenie v antennykh reshetkakh [Adaptation and Superresolution in Antenna Arrays]. Moscow: Radio i svyaz', 2003. 200 p. (In Russ.).
2. Zhuravlev A.K., Hlebnikov V.A., Rodimov A.P. et al. Adaptivnye radiotekhnicheskie sistemy s antennymi reshetkami [Adaptive Radio Engineering Systems with Antenna Arrays]. Leningrad: LenGU Publishing, 1991. 544 p. (In Russ.).
3. Monzingo R.A., Miller T.U. Adaptivnye antennye reshetki [Adaptive Antenna Arrays]. Moscow: Radio and communication, 1986. 448 p. (In. Russ.).
4. Compton R.T. Adaptive antennas. Englewood Cliffs, N.Y.: Prentice-Hall, 1988. 400 p.
5. Ivanov D. V., Ivanov V. A., Katkov E. V. et al. Dal'nee upravlenie eksperimentom po naklonnomu zondirovaniyu ionosfernykh kanalov KV-svyazi [Remote Control of the Experiment on the Oblique Sounding of Ionospheric Channels of Short-Wave Communication]. Vestnik Povolzhskogo gosudarstvennogo tekhnologicheskogo universiteta. Ser.: Radiotekhnicheskie i infokommunikatsionnye sistemy [Vestnik of Volga State University of Technology. Ser.: Radio Engineering and Infocommunication Systems]. 2016. No 3 (31). Pp. 18-30. (In Russ.).
6. Ivanov V.A., Ivanov D.V., Ryabova N.V. et al. Issledovanie kharakteristik peremeshchayushchikhsya ionosfernykh vozmushcheniy metodom naklonnogo zondirovaniya verkhney atmosfery zemli [Research on the Characteristics of Traveling Ionospheric Disturbances Using the Technique of the Oblique Sounding of the Upper Earth Atmosphere]. Fizika volnovykh protsessov i radiotekhnicheskie sistemy [Physics of Wave Processes and Radio Engineering Systems]. 2015. Vol. 18, No 3-2. Pp. 92-97.
(In Russ.).
7. Ivanov V. A., Ivanov D. V., Ryabova N. V. et al. Pervichnaya obrabotka ionogramm naklonnogo zondirovaniya ionosfery [Initial Processing of Oblique Ionospheric Sounding Ionograms]. Vestnik Povolzhskogo gosudarstvennogo tekhnologicheskogo universiteta. Ser.: Radiotekhnicheskie i infokommunikatsionnye sistemy [Vestnik of Volga State University of Technology. Ser.: Radio Engineering and Infocommunication Systems]. 2015. No 2 (26). Pp. 19-26. (In Russ.).
8. Ivanov V. A., Ryabova N. V., Ivanov D. V., Sushentsov R. A., Ryabova M. I., Chernov A. A. Issledovanie vliyaniya modeley mnogoluchevosti na strukturnye funktsii ionosfernykh dekametrovykh kanalov radiosvyazi [Investigation of the Influence of Multipath Models on Structure Functions of Ionospheric Decameter Channels of Radio Communication]. Vestnik Povolzhskogo gosudarstvennogo tekhnologicheskogo universiteta. Ser.: Radiotekhnicheskie i infokommunikatsionnye sistemy [Vestnik of Volga State University of Technology. Ser.: Radio Engineering and Infocommunication Systems]. 2015. No 4 (28). Pp. 6-17. (In Russ.).
9. Osovsky S. Neironnye seti dlya obrabotki informatsii [Neural Networks for Information Processing]. Translation from Polish I. D. Rudinsky. Moscow: Finance and statistics, 2002. 344 p. (In Russ.).
10. Medvedev V.S., Potemkin V.G. Neironnye seti. MATLAB 6 [Neural Networks. MATLAB 6] / Edited by Candidate of Engineering Sciences V.G. Potemkin. Moscow: DIALOG-MIFI, 2002. 496 p. (In Russ.).
11. Zooghby A. H., Christodoulou C. G., and Georgiopoulos M. Performance of radial basis func-tion networks for direction of arrival estimation with Antenna Arrays. IEEE Trans. Antennas Propagat. Nov. 1997. Vol. 45. Pp. 1611–1617.

For citation: Nasybullin A. R., Vedenkin D. A. Spatial Filtering of Ionospheric Modes in an Adaptive Antenna Based on Neural Network Technologies. Vestnik of Volga State University of Technology. Ser.: Radio Engineering and Infocommunication Systems. 2017. No 4 (36). Pp. 26-32. DOI: 10.15350/2306-2819.2017.4.26