DOI 10.17586/0021-3454-2020-63-3-199-205
UDC 681.511.4
Method for Refining a Priori Probabilities of a Complex System States from Experimental Data
A. F. Mozhaysky Military Spaсe Academy, Department of Onboard Information and Measuring Complexes; Professor
A. B. Petukhov
A. F. Mozhaysky Military Space Academy, Department of Airborne Information and Measurement Complexes; Lecturer
A. A. Yadrenkin
A. F. Mozhaisky Military Space Academy, Department of On-board Information and Measuring Complexes; Associate Professor
Read the full article
Abstract. For a complex system, the problem of refining a priori probabilities of hypotheses about the system state using the data obtained during its experimental adjustment and operation is considered. The proposed method for solving this problem is based on weighted accounting of the results of a priori and experimental studies of the system. The results of comparing a posteriori estimates with estimates obtained by Bayes formulas are presented. It is shown that, in contrast to the Bayesian solution, the use of the proposed method provides for accounting the proximity of the results of a priori studies of the system to the results of experiments, and does not allow a priori information to dominate the experimental data.
References:
1. Tsypkin Ya.Z. Informatsionnaya teoriya identifikatsii (Information Identification Theory), Moscow, 1995, 336 р. (in Russ.)
2. Merkov A.B. Raspoznavaniye obrazov. Postroyeniye i obucheniye veroyatnostnykh modeley (Pattern Recognition. Building and Training Probabilistic Models), Moscow, 2014, 240 р. (in Russ.)
3. Buryak Yu.I., Skrynnikov А.А. Nauchnyi Vestnik MGTUGA, 2015, no. 10(220), pp. 47–54. (in Russ.)
4. Fomin Ya.A. Raspoznavaniye obrazov: teoriya i primeneniya (Pattern Recognition: Theory and Applications), Moscow, 2012, 429 р. (in Russ.)
5. Ventcel E.S. Teoriya veroyatnostey (Probability Theory), Moscow, 2003, 576 p. (in Russ.)
6. Pugachev V.S. Teoriya veroyatnostey i matematicheskaya statistika (Probability Theory and Mathematical Statistics), Moscow, 2002, 496 р. (in Russ.)
7. Frolenkov K.V. Trudy SPIIRAN (SPIIRAS Proceedings), 2013, no. 1(24), рр. 152–164. (in Russ.)
8. Dorozhko I.V., Tarasov A.G., Baranovskiy A.M. Intellectual Technologies on Transport, 2015, no. 3, pp. 36–45. (in Russ.)
9. Tulupyev A.L. Vestnik of Saint Petersburg University. Applied mathematics. Computer Science.
Control Processes, 2012, no. 2, pp. 51–59. (in Russ.)
10. Kahneman D. et al. Judgment under Uncertainty: Heuristics and Biases, 21st. Cambridge University Press, 2005, 555 p.
11. Aleksandrovskaya L.N., Kruglov V.I., Kuznetsov A.G. et al. Teoreticheskiye osnovy ispytaniy i eksperimental'naya otrabotka slozhnykh tekhnicheskikh sistem (Theoretical Basis of Testing and Experimental Testing of Complex Technical Systems), Moscow, 2003, 736 р. (in Russ.)
12. Arsen'ev V.N. Otsenivanie kharakteristik sistem upravleniya po ogranichennomu chislu naturnykh ispytaniy (Estimation of Characteristics of Control Systems on Limited Number of Full-Scale Tests), Moscow, 2013, 126 p. (in Russ.)
13. Dmitriyev A.K., Yusupov R.M. Identifikatsiya i tekhnicheskaya diagnostika (Identification and technical diagnostics), Leningrad, 1987, 521 р. (in Russ.)
14. Korolyuk V.S., Portenko N.I., Skorokhod A.V., Turbin A.F. Spravochnik po teorii veroyatnostey i matematicheskoy statistike (Reference Book on Probability Theory and Mathematical Statistics), Moscow, 1985, 640 р. (in Russ.)
15. Ravindran A., Ragsdell K.M. and Reklaitis G.V. Engineering Optimization: Methods and Applications, John Wiley & Sons, 2006, 681 р.
16. Greene W.H. Econometric analysis, NY, Pearson Education, Inc., 2003, 1026 p.
17. Arsen'ev V.N., Labetskiy P.V. Journal of Instrument Engineering, 2014, no. 10(57), рр. 23–28. (in Russ.)
