Rumyantsev N.V., Solovyov S.V., Pavlov D.V. An intelligent system for monitoring, diagnosing and predicting the condition of on-board spacecraft systems

Аuthors

Rumyantsev N. ^*, Solovyov S. ^**, Pavlov D. V.^***

S. P. Korolev Rocket and Space Corporation «Energia», 4A Lenin Street, Korolev, Moscow area, 141070, Russia

*e-mail: rumancevnikita39@gmail.com
**e-mail: sergey.soloviev@scsc.ru
***e-mail: dmitripavlov@inbox.ru

Abstract

The reliability of spacecraft (SC) flight control depends on making optimal and operational decisions on issuing command actions to the SC. Practice shows that in some cases, only issuing immediate execution commands can prevent the development of emergency situations (ESS). The correctness of solutions to such problems is increased by using artificial intelligence methods as part of the ground control complex (GCS), the use of which is aimed at accelerating the processes of identifying anomalies, increasing the accuracy and completeness of recognition of GSNs in the operation of on-board spacecraft systems, and reducing the influence of the “human factor”. The article examines the state of control technologies currently used in flight control of modern spacecraft. The main shortcomings of the control process are formulated, which are increasing taking into account modern trends in the development of space programs.
An intellectualized system for monitoring, diagnosing and predicting the state of on-board spacecraft systems is proposed, based on the use of artificial neural networks (ANN) technology, which includes a system for analyzing telemetric information (TMI) using artificial neural network technology (application stage) and a system for synthesizing artificial neural networks, preparing training and test data sets, training and creating computer applications (training stage). For each component of the spacecraft, the use of a set of neural networks based on a single platform is provided. The neural network synthesis system is an artificial intelligence (AI) platform and is intended for the creation, development, testing and technical support of neural networks, and is focused on minimizing specific tasks in the field under consideration, such as data collection, organizing machine learning processes and deployment for various scenarios use.

Keywords:

spacecraft, flight control, intelligent system, artificial intelligence, artificial neural networks, training data set

References

1. Abanin O.I., Solov'ev S.V. Inzhenernyi zhurnal: Nauka i innovatsii, 2019, no. 6. DOI: 10.18698/2308-6033-2019-6-1890
2. Kovalenko A.A., Pirogov P.V., Skurskii Yu.A., Solov'ev S.V., Stanilovskaya V.I. Kosmonavtika i raketostroenie, 2018, no. 5 (104), pp. 36-47.
3. Solov'ev V.A., Lyubinskii V.E., Zhuk E.I. Pilotiruemye polety v kosmos, 2011, no. 2 (2), pp. 30–46.
4. Abramov N.S., Talalaev A.A., Fralenko V.P. Informatsionnye tekhnologii i vychislitel'nye sistemy, 2016, no. 1, pp. 64–75.
5. Abramov N.S., Zadneprovskii V.F., Talalaev A.A., Fralenko V.P. Sovremennye problemy nauki i obrazovaniya, 2014, no. 3, pp. 62.
6. Loskutov A.I., Vecherkin V.B., Shestopalova O.L. Informatsionno-upravlyayushchie sistemy, 2012, no. 2, pp. 74-81.
7. Bakhtadze N., Lototsky V., Pyatetsky V., Lototsky A. Identification Algorithms Basedonthe Associative Search of Analogs and Association Rules, Proc. Int. Conf. Time Ser. Forecast (ITISE 2018), Granada, Spain, 19–21 September, 2018, rr. 783–794.
8. Balukhto A.N., Romanov A.A. Raketno-kosmicheskoe priborostroenie i informatsionnye sistemy, 2019, vol. 6, no. 1, pp. 65–75.
9. Eremin D.M., Gartseev I.B. Iskusstvennye neironnye seti v intellektual'nykh sistemakh upravleniya (Artificial neural networks in intelligent control systems), Moscow, MIREA, 2004, 75 p.
10. Novikova D.A. Teoriya upravleniya (dopolnitel'nye glavy) Control theory (additional chapters), Moscow, Lenand, 2019, 552 p.
11. Gorozhanina E.I. Neironnye seti (Neural networks), Samara, PGUTI, 2017, 84 p.
12. Qu C. et al. Predictive anomaly detection for marine diesel engine based on echo state network and autoencoder, Energy Reports, Elsevier Ltd, 2022, vol. 8, pp. 998-1003. DOI: 10.1016/j.egyr.2022.01.225
13. Wang H. et al. Anomaly detection for hydropower turbine unit based on variational modal decomposition and deep autoencoder, Energy Reports, Elsevier Ltd, 2021, vol. 7, pp. 938–946. DOI: 10.1016/j.egyr.2021.09.179
14. Goreva T.I., Pornyagin N.N., Pyukke G.A.. Vestnik Kamchatskoi regional'noi assotsiatsii «Uchebno-nauchnyi tsentr», 2012, no. 1 (4), pp. 31–43.
15. Sai Van Kvong, Shcherbakov M.V. Prikaspiiskii zhurnal: upravlenie i vysokie tekhnologii, 2019, no. 1 (45), pp. 33-44.
16. Sukhanov N.V. Trudy MAI, 2013, no. 65. URL: http://trudymai.ru/eng/published.php?ID=36013
17. Kosinskii M.Yu., Shatskii M.A. Trudy MAI, 2014, no. 74. URL: http://trudymai.ru/eng/published.php?ID=49315
18. Dorozhko I.V., Osipov N.A., Ivanov O.A. Trudy MAI, 2020, no. 113. URL: http://trudymai.ru/eng/published.php?ID=118181. DOI: 10.34759/trd-2020-113-14
19. Dorozhko I.V., Ivanov O.A. Trudy MAI, 2021, no. 118. URL: https://trudymai.ru/eng/published.php?ID=158259. DOI: 10.34759/trd-2021-118-19
20. Nazarov A.V., Loskutov A.I. Neirosetevye algoritmy prognozirovaniya i optimizatsii sistem (Neural network algorithms for forecasting and optimization of systems), Saint Petersburg, Nauka i tekhnika, 2003, 384 p.

Download