Decision-making support system model for spacecraft onboard systems diagnosing based on Bayesian networks

DOI: 10.34759/trd-2021-118-19

Аuthors

Dorozhko I. V.^*, Ivanov O. A.^**

Mlitary spaсe Aсademy named after A.F. Mozhaisky, Saint Petersburg, Russia

*e-mail: Doroghko-Igor@yandex.ru
**e-mail: kompa4ka@yandex.ru

Abstract

The article proposes employing Bayesian networks capabilities, based on non-uniform data as well as fragments of knowledge representation and posteriori inference for the incoming information accounting, to solve the problems of the spacecraft onboard systems diagnosing.

The developed model and technique are based on mathematical apparatus of Bayesian trust networks, as well as the basic concepts and relationships of the theory of reliability and technical diagnostics of systems. The initial data is information on the reliability (structural and logical schemes, failure rate of elements) of spacecraft typical onboard systems and diagnostic models that linking the types of technical conditions and diagnostic features. For cause-and-effect relationships between the types of technical condition and diagnostic features, sets of conditional probabilities or densities of distributions are pointed, depending on the continuous or discrete type of diagnostic feature, respectively.

The results of the research are constructing technique and a model of an intelligent decisions support system for a spacecraft onboard systems diagnosing.

The article considers examples of new incoming information processing in a fragment of the Bayesian network at diagnosing spacecraft onboard systems. It quotes analytical calculations and posteriori inference results while new information incoming on the spacecraft blocks failures, as well as while incoming of discrete and continuous values of diagnostic features.

The model based on dynamic hybrid Bayesian trust networks includes discrete and continuous variables describing causal relationships of technical conditions and diagnostic features types, as well as relationships of blocks (elements) in terms of reliability. The results of the logical-probabilistic inference allow control the values of the spacecraft operational state probabilities in the course of time, as well as predict possible failures and take proactive measures.

Mathematical models of diagnosing, considered in the article, account for the types of elements connection, reliability of elements, as well as dynamics of technical states types and their relation to the diagnostic features, which may be both continuous and discrete.

Keywords:

intelligent decision-making support system, spacecraft, diagnostics, Bayesian network

References

1. Kobzarev I.M. Kopkin E.V. Trudy Voenno-kosmicheskoi akademii im. A.F. Mozhaiskogo, 2019, no. 671, pp. 326 — 337.

2. Miller G.A. The magical number seven, plus or minus two: Some limits on our capacity for processing information, Psychological Review, 1956, no. 63 (2), pp. 81 — 97.

3. GOST V 20.911 89. Tekhnicheskaya diagnostika. Terminy i opredeleniya (State Standard V 20911-89. Technical diagnostics. Terms and definitions), Moscow, Standarty, 1990, 12 p.

4. Klyuev V.V. et al. Tekhnicheskie sredstva diagnostirovaniya: Spravochnik (Diagnostic Facilities: Handbook), Moscow, Mashinostroenie, 1989, 671 p.

5. Sukhanov N.V. Trudy MAI, 2013, no. 65. URL: http://trudymai.ru/eng/published.php?ID=36013

6. Kosinskii M.Yu., Shatskii M.A. Trudy MAI, 2014, no. 74. URL: http://trudymai.ru/eng/published.php?ID=49315

7. Tulup’ev A.L., Nikolenko S.I., Sirotkin A.V. Osnovy teorii baiesovskikh setei. (Fundamentals of Bayesian networks theory), Saint-Petersburg, Izd-vo Sankt-Peterburgskogo universiteta, 2019, 399 p.

8. Cowell R.G., Dawid A.P., Lauritzen S.L., Spiegelhalter D.J. Probabilistic Networks and Expert Systems, New York, Springer-Verlag, 1999. DOI:10.1198/JASA.2001.S424

9. Jensen F.V. Bayesian Networks and Decision Graphs, New York, Springer-Verlag, 2001. DOI:10.1007/978-1-4757-3502-4

10. Pearl J. Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference, New York, Morgan Kaufman Publ., 1991. DOI:10.2307/2026705

11. 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

12. Nikolenko S., Kadurin A., Arkhangel’skaya E. Glubokoe obuchenie (Deep learning), Saint Petersburg, Piter, 2018, 480 p.

13. Dorozhko I.V., Zakharova E.A., Osipov N.A. Trudy Voenno-kosmicheskoi akademii im. A.F. Mozhaiskogo, 2019, no. 669, pp. 216 — 223.

14. GeNIe & SMILE. Decisions systems laboratory, School of Information Sciences, University of Pittsburg. URL: http://genie.sis.pitt.edu

15. GOST 27.002-15. Nadezhnost’ v tekhnike. Osnovnye ponyatiya. Terminy i opredeleniya (State Standard 27.002-15. Reliability in technology. Concepts. Terms and definitions.), Moscow, Standartinform, 2016, 24 p.

16. Dmitriev A.K. Modeli i metody analiza tekhnicheskogo sostoyaniya bortovykh system (Models and methods of onboard systems technical condition analysis: training manual), Saint Petersburg, VIKU imeni A.F. Mozhaiskogo, 1999, 171 p.

17. Dmitriev A.K., Kopkin E.V. Izvestiya vuzov. Priborostroenie,1999, vol. 42, no. 9, pp. 3 — 10.

18. Dmitriev A.K, Yusupov R.M. Identifikatsiya i tekhnicheskaya diagnostika vvuzov (Identification and technical diagnostics: a textbook for universities), Leningrad, MO SSSR, 1987, 521 p.

19. Kopkin E.V., Kravtsov A.N., Myshko V.V. Analiz tekhnicheskogo sostoyaniya kosmicheskikh sredstv (Analysis of space assets technical condition), Saint Petersburg, VKA imeni A.F. Mozhaiskogo, 2016, 189 p.

20. Kopkin E.V., Kravtsov A.N., Myshko V.V. Kontrol’ i diagnostika kosmicheskikh sredstv (Control and diagnosis of space facilities: a training manual), Saint Petersburg, VKA imeni A.F. Mozhaiskogo, 2016, 198 p.

21. Okhtilev M.Yu., Sokolov B.V., Yusupov R.M. Izvestiya YuFU. Tekhnicheskie nauki, 2015, no. 1 (162), pp. 162 — 174.

22. Okhtilev M.Yu., Mustafin N.G., Miller V.E., Sokolov B.V. Izvestiya vuzov. Priborostroenie, 2014, vol. 57, no. 11, pp. 7 — 15.

23. Motienko A., Basov O., Dorozhko I., TarasovA. Proactive Robotic Systems For Effective Rescuing Sufferers, GmbH: Springer-Verlag, Lecture Notes In Computer Science, 2016, pp. 172 — 180.

    
    Download