Application of neural networks to the analysis of the motion of a space tether system


Аuthors

Akalu Y. A.1, Wang C. 2, Dmitry V. E.1, Lu H. 2

1. Samara National Research University named after Academician S.P. Korolev, Moskovskoe shosse, 34, Samara, Russia
2. Northwestern Polytechnical University, 710072, 127, West Youyi Road, Beilin District, Xi'an Shaanxi, P.R.China

Abstract

The research considers the application of neural networks for the analysis of the stability of the tether system motion in the atmosphere and for the analysis of the tether system deployment process in the atmosphere. The analysis is performed using multilayer neural networks, forward and backward error propagation methods, and two different activation functions to minimize training errors. The training process was carried out using a different number of perceptrons in the hidden layer until the system produced results that matched those expected based on direct calculations. To train the neural network, input and output (target) data are used that were previously obtained using numerical calculations using a mathematical model of the space tether system motion. Since the motion parameters of the tether system include the parameters of two rigid bodies and the tether, it turned out to be possible to reduce the problem to training the neutron network using individual tether system parameters, primarily the angular coordinates of the bodies included in the system. The choice of angular coordinates is justified by the fact that they are decisive in the analysis of motion stability, and a conclusion about the stability of the motion is made basing on changes in their amplitudes over time. The results of the research showed that the neural network, after learning to calculate the trajectory of the motion of the tether system, allows to significantly reduce the time needed for the analysis of the stability of the system's motion and makes it possible to correct errors after learning the neural network.

Keywords:

neural network, tether system, aerodynamic stabilization, mean squared error

References

  1. Abdul-Wahaba S.A., Al-Alawi S.M. Assessment and prediction of tropospheric ozone concentration levels using artificial neural networks. Environmental Modelling & Software. 2002. V. 17, P. 219–228. DOI: 10.1016/S1364-8152(01)00077-9
  2. William E. Faller, Scott J. Schreck. Neural networks: application and opportunities in aeronautics. Progress in Aerospace Sciences. 1996. V. 32, P. 433-456. URL: https://doi.org/10.1016/0376-0421(95)00011-9
  3. Alekseev V.I., Shevkunov I.A. Application of Neural Network Technology in Aerospace Industry Annotation. Vestnik Rossiiskogo novogo universiteta. 2020. No. 4. P. 32-42. (In Russ.). DOI: 10.25586/RNU.V9187.20.04.P.032
  4. Shirobokov M.G., Trofimov S.P. Formation control in low-Earth orbits by means of machine learning methods. Preprinty IPM im. M.V. Keldysha. 2020. No. 19. (In Russ.). (In Russ.). URL: http://doi.org/10.20948/prepr-2020-19 
  5. Sorokin A.V., Shirobokov M.G. Correction and prediction of the spacecraft’s orbital motion by artificial neural networks. Preprinty IPM im. M.V.Keldysha. 2018. No. 198. (In Russ.). DOI: 10.20948/prepr-2018-198 
  6. Rafiq M.Y., Bugmann G., Easterbrook D.J. Neural network design for engineering application. Computers and structures. 2001. No. 79. P. 1541-1552. DOI: 10.1016/S0045-7949(01)00039-6
  7. Aditya Kumar, Rahul Chhibber. Investigation of the wetting behavior of formulated SMAW electrode coating fuxes with regression and ANN model. Metallurgical and Materials Transactions. 2022. V. 54, P. 287-302. DOI: 10.1007/s11663-022-02689-x
  8. Zabolotnov Yu.M., Elenev D.V. Motion in an atmosphere of tether system landing module – aerodynamic stabilizer. Izvestiya Samarskogo nauchnogo tsentra Rossiiskoi akademii nauk. 2006. V. 8, No. 3. P. 833-840. (In Russ.)
  9. Elenev D.V., Zabolotnov Yu.M. Analysis of the dynamics of the deployed aerodynamic space tether system. Cosmic Research. 2017. V. 55, No. 5. P. 371-379. (In Russ.). DOI: 10.1134/S0010952517050057
  10. Akalu Y. Aynwaga, Elenev D.V. Stability Analysis of Motion of Tether System in Atmosphere with Variable Tether Length. Russian Engineering Research. 2024. V. 44, No. 12. P. 1701–1706.
  11. Akalu I.A., Elenev D.V. Methods for modelling the motion of tether system. Nauka i biznes: puti razvitiya. 2023. No. 4 (142). P. 8–11. (In Russ.).
  12. V'yugin V.V. Matematicheskie osnovy mashinnogo obucheniya i prognozirovaniya. (Mathematical foundations of machine learning and forecasting). Moscow: MTSNMO Publ., 2014. 304 p.
  13. Kirillov A.V., Desta A.B., Dubbessa M.Kh., Akalu I.A. Application of neuratl networks for diagnosing and preventing sensor failures of a turbojet bypass engine. Perspektivy nauki. 2021. No. 11 (146). P. 35-37. (In Russ.)
  14. Bel'skii A.B. Requirements for on-board optical-electronic means of aerial reconnaissance of aircraft. Trudy MAI. 2022. No. 123. (In Russ.). URL: https://trudymai.ru/eng/published.php?ID=165561. DOI: 10.34759/trd-2022-123-16
  15. Grishelenok D.A., Kovel' A.A. The neural network use in internal measuring system for satellite’s equipment. Issledovaniya naukograda. 2013. No. 1. P. 9-13. (In Russ.)
  16. Dorofeev E.A., Dynnikov A.I., Kargopol'tsev A.V., Sviridenko Yu.N., Fadeev A.S. Application of artificial neural networks for processing and analysis of aerodynamic experiment data. Uchenye zapiski TSAGI. 2007. V. XXXVIII, No. 3-4. P. 111-118. (In Russ.)
  17. Sokolov D.Yu. Application of artificial neural network for solving problems of forecasting the movement of ground objects. Trudy MAI. 2022. No. 123. (In Russ.). URL: https://trudymai.ru/eng/published.php?ID=165563. DOI: 10.34759/trd-2022-123-17
  18. Osovskii S. Neironnye seti dlya obrabotki informatsii (Neural networks for information processing). Moscow: Finansy i statistika, 2004. 343 p.
  19. Ivashova N.D., Mikhailin D.A., Chernyakova M.E., Shanygin S.V. Neural network solution of the operational planning task for unmanned aerial vehicles route flight and time setting for ground based objects observation employing the fuzzy logic while displaying these results on the computer screen prior to the start. Trudy MAI. 2019. No. 104. (In Russ.). URL: http://trudymai.ru/eng/published.php?ID=102223 
  20. Christopher M. Bishop. Neural Networks for Pattern Recognition, Oxford Univ. Press, 1995, 498 p.


Download

mai.ru — informational site MAI

Copyright © 2000-2025 by MAI

 Вход