Nguyen Thanh Long1

1 Scientific Research Institute of Rocket Technology (Hanoi, Vietnam)

1 nguyenthanhlong_676@yahoo.com

Problem setting. Neural network modeling of design solutions for the development of an unmanned aerial vehicle (UAV) under the influence of uncontrollable factors requires solving the problem of choosing rational (optimal) design solutions (parameters) of a UAV using fuzzy logic methods. Solving the problem of selecting the optimal design parameters of a UAV using the fuzzy logic method is implemented using neural network optimization of design solutions in terms of fuzzy logic and is an effective tool in the development of modern UAVs.

Target. To develop a neural network approach to the selection of design solutions (parameters) of a UAV operating under conditions of uncertainty factors (uncontrollable) to increase the efficiency of performing target tasks.

Results. This approach is the basis for the development of a method for generating UAV design solutions that are resistant to multifactorial uncertainty. The proposed approach allows us to solve further problems such as the formation of design decisions (parameters) in terms of fuzzy logic and fuzzy inference, the development of a mathematical model of UAVs for the formation of statistical samples necessary for training artificial neural networks (ANN), etc.

Practical significance. The obtained result allows us to use this approach for the statistical synthesis of UAV elements in neuro-fuzzy systems.

Nguyen Thanh Long Neuro-fuzzy approach to choosing design solutions for developing a drone. Neurocomputers. 2024. V. 26. № 1. Р. 45-53. DOI: https://doi.org/10.18127/j19998554-202401-05 (In Russian)

1. Petushkov A.M., Samokhvalov O.A. Methodological approach to improving the effectiveness of monitoring large-area emergency zones by a group of autonomous unmanned aerial vehicles. Science Intensive Technologies. 2022. V. 23. № 1. P. 35−41. DOI 10.18127/ j19998465-202201-05. (in Russian)
2. Pozdyshev V.Yu., Timoshenko A.V., Razinkov S.N., Razinkova O.E. Estimates of angular coordinates and location of radio emission sources using phase direction finders on unmanned aerial vehicles. Information measuring and control systems. 2020. V. 18. № 4. P. 58–67. DOI 10.18127/j20700814-2004-07. (in Russian)
3. Shaidullin Z.F., Tesevich S.F., Bogdanovsky S.V., Simonov A.N. Spatial polarization processing of radio signals during bearing of radio emission sources from an unmanned aerial vehicle. Electromagnetic waves and electronic systems. 2022. V. 27. № 3. P. 4–9. (in Russian)
4. Balyk V.M. Statistical synthesis of design solutions in the development of complex systems. Moscow: MAI. 2011. 280 p. (in Russian)
5. Wasserman F. Neurocomputer technology: Theory and practice. Moscow: Mir. 1992. 184 p. (in Russian)
6. Vasiliev A.N., Tarkhov D.A. Neural network modeling. Principles. Algorithms. Appendices. St. Petersburg: SPbGPU. 2009. 528 p. (in Russian)
7. Tarkhov D.A. Neural network models and algorithms: Handbook. M.: Radio Engineering. 2014. 349 p. (in Russian)
8. Galushkin A.I. Theory of neural networks. M.: IPRZHR. 2000. 415 p. (in Russian)
9. Terekhov V.A., Efimov D.V., Tyukin I.Yu. Neural network control systems. Moscow: IPRZHR. 2002. 480 p. (in Russian)
10. Balyk V.M., Vedernikov K.V., Kulakova R.D. Statistical synthesis of a multipurpose system of aircraft of optimal type. Flight. All-Russian Scientific and Technical Journal. 2014. № 5. P. 11–18. (in Russian)
11. Balyk V.M., Ilyichev A.V., Sorokin V.A. Methods of making design decisions based on models of the effectiveness of a two-medium aircraft: Textbook. Moscow: MAI. 2015. 220 p. (in Russian)
12. Piyavsky S.A., Brusov B.C., Khvilon E.A. Optimization of parameters of multipurpose aircraft. M.: Mechanical engineering. 1974. 168 p. (in Russian)
13. Tarasov E.V. Algorithms for optimal design of aircraft. M.: Mechanical engineering. 1970. 364 p. (in Russian)
14. Tseverov D.N. Design of unmanned aerial vehicles. M.: Mechanical engineering. 1978. 264 p. (in Russian)
15. Tarasov E.V., Balyk V.M. Methods of designing aircraft: Textbook. M.: MAI. 2006. 96 p. (in Russian)
16. Brusov B.C., Baranov S.K. Optimal design of aircraft. A multi-purpose approach. M.: Mechanical engineering. 1989. 230 p. (in Russian)
17. Matveev Yu.A., Lamzin V.V. Method of selecting design parameters for modifications of spacecraft for remote sensing of the Earth in the presence of limitations. Bulletin of the Moscow Aviation Institute. 2008. V. 15. № 1. P. 12. (in Russian)
18. Nguyen K.T., Wu A.H., Yagodkina T.V. The task of combined UAV control in conditions of multifactorial uncertainty. Radio engineering. 2020. V. 84. № 1(2). P. 55–61. DOI 10.18127/j00338486-2001(02)-06. (in Russian)
19. Thuong N.Q. Method of Combining the Synthesis of Program Control with Homing Methods for the Problem of UAV’s Control in Conditions of Multifactorial Uncertainty. International Conference on Engineering and Telecommunication. Dolgoprudny, Russia. 2019. P. 1–4. DOI 10.1109/EnT47717.2019.9030572.
20. Balyk V.M., Thuong N.Q. Statistical Synthesis of the Principle of Rational organization of a Complex Technical System. International Conference on Engineering and Telecommunication. Dolgoprudny, Russia. 2019. P. 1–4. DOI 10.1109/EnT47717.2019.9030569.
21. Bezverbny V.K., Zernov V.I., Perelygin B.P. The choice of design parameters of aircraft: Textbook. M.: MAI. 1984. 375 p. (in Russian)
22. Rutkovskaya D., Pilinsky M., Rutkovsky L. Neural networks, genetic algorithms and fuzzy systems. M.: Hotline – Telecom. 2006. 452 p. (in Russian)
23. Borisov A.N., Alekseev A.V., Krumberg O.A., etc. Decision-making models based on a linguistic variable. Riga: Zinatne. 1982. 256 p. (in Russian)
24. Yakhyaeva G. Fuzzy sets and neural networks. M.: INTUIT. 2016. 187 p. (in Russian)
25. Belozerova G.I., Skudnev D.M., Kononova Z.A. Fuzzy logic and neural networks: A textbook. Part 1. Lipetsk: LGPU. 2017. 62 p. (in Russian)
26. Bodyansky E.V., Rudenko O.G. Artificial neural networks: architectures, training, applications. Kharkiv: Teletech. 2004. 369 p. (in Russian)