A.G. Volkov - Ph.D. (Eng.), Associate Professor; Financial University under Government of Russian Federation E-mail: avolkov@fa.ru A.I. Polous - Ph.D. (Eng.) Professor V.I. Goncharenko - Dr.Sc. (Eng.), Associate Professor, Director of Military Institute, Moscow Aviation Institute (National Research University); Lead Engineer, V.A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences E-mail: vladimirgonch@mail.ru M.A. Ikonnikov - Post-graduate Student, Moscow Aviation Institute (National Research University) E-mail: maxim.ikonnikov@gmail.com

The results of these studies showed that those who were in the habit of using high quality and reliability, Traditional estimation algorithms, despite the high versatility, has low operational decision making, especially with growing completeness of classes of technical states. It is the use of the neural network technology for the treatment of neural network and traditional algorithms. The application of the algebraic approach in solving the problem of the synthesis of functional diagnostics that allows you to simulate a multi-layered network of two-layer network. The results of the analysis of existing neural networks and types of neu-rons, which are allowed on the basis of a four-probabilistic neural net-work PNN , where as the second layer of a so-called competitive layer. The necessity of using probabilistic network, which is caused by fuzzy (probabilistic) character input situations. At the same time the competing layer calculates the probability of the input of the vector, belongs to the particular class, and ultimately puts the fuzzy input vector according to the class. This experiment is supported by the feasibility of using probabilistic PNN network type as a model for the decision on the reconfiguration of onboard equipment, under certain statistical data on the distribution of a class of decisions and the corresponding samples of neurons. This makes it possible to establish a surface between classes of technical states. The developed neural network algorithm for computing the theses the advantages of the traditional estimation algorithms as the versatility and advantage of neural networks. The proposed algorithm is implemented in software of the functional diagnosis of the onboard equipment of modern aircrafts.

 

1. Nejjlor Kris. Kak postroit mashinu vyvoda // EHkspertnye sistemy. M.: Radio i svjaz. 1987.
2. ZHuravlev JU.I. Ob algoritmicheskom podkhode k resheniju zadach raspoznavanija i klassifikacii // Problemy kibernetiki. 1978. Vyp. 38.
3. Kruglov V.V., Borisov V.V. Iskusstvennye nejjronnye seti. Teorija i praktika. M.: Gorjachaja linija-Telekom. 2001.
4. Gorban A.N. Obuchenie nejjronnykh setejj. M.: SP «ParaGraf». 1990.
5. Pontrjagin L.S. Osnovy kombinatornojj topologii. M.: Nauka. 1986.
6. Arkanov A.V., Goncharenko V.I., Kobzar A.A. Opredelenie prichin neshtatnogo funkcionirovanija ballisticheskogo obekta // Izv. Instituta inzhenernojj fiziki. 2012. № 2 (24). S. 8-10.
7. Nechaev V.V., Goncharenko V.I., Rozhnov A.V., Lychev A.V., Lobanov I.A. Integracija komponentov virtualnojj semanticheskojj sredy i obobshhjonnojj modeli analiza sredy funkcionirovanija // Sovremennye informacionnye tekhnologii i IT-obrazovanie. 2016. T. 12. № 3. CH. 1. S. 187-194.
8. Ogandzhanjan S.B., Rozhnov A.V., Burmistrov P.A., Lobanov I.A., Tjurin S.A. Tvorcheskie materialy «kruglogo stola». CH. I. Retrospektiva i realnaja konkordancija issledovanijj v sfere intellekta // Nejjrokompjutery: razrabotka, primenenie. 2016. № 1. S. 17-29.
9. Rozhnov A.V. Tvorcheskie materialy «kruglogo stola». CH. II. Sistemnaja integracija i modelirovanie novykh ehffektov v sfere intellekta // Nejjrokompjutery: razrabotka, primenenie. 2016. № 3. S. 3-12.
10. Goncharenko V.I., Legovich JU.S., Ryvkin S.E. Obrabotka telemetricheskojj informacii o kinematicheskikh parametrakh dvizhenija letatelnykh apparatov na osnove diskretnogo vejjvlet-preobrazovanija // Doklady XVIII Mezhdunar. konferencii. Ser. Cifrovaja obrabotka signalov i ejo primenenie - DSPA-2016. (Moskva, 30 marta - 01 aprelja 2016 g.). 2016. T. 1. Vyp. XVIII-1. M.: RNTOREHS imeni A.S. Popova. S. 442-447.
11. Rozhnov A.V., Lobanov I.A., Bimakov E.V. Obosnovanie zadach sistemnojj integracii i informacionno-analiticheskoe modelirovanie problemno-orientirovannykh sistemy upravlenija na predproektnom ehtape zhiznennogo cikla / Trudy XII Vserossijjskogo soveshhanija po problemam upravlenija (VSPU-2014, Moskva). M.: IPU RAN. 2014. S. 7474-7479.
12. Rozhnov A.V., Gubin A.N., Mikhajjlov R.A., Belavkin P.A. Stanovlenie vychislitelnykh sistem i kompleksov voennogo naznachenija na zare strategicheskikh raketnykh vojjsk // Nejjrokompjutery: razrabotka, primenenie. 2010. № 11. S. 62-68.
13. Goncharenko V.I., Kobzar A.A., Korneev A.A., Kucherjavenko D.S. Algoritm ocenivanija kharakteristik ballisticheskogo obekta pri neizvestnykh parametrakh ego matematicheskojj modeli dvizhenija i nekachestvennojj izmeritelnojj informacii // Vestnik Kazanskogo gosudarstvennogo tekhnicheskogo universiteta im. A.N. Tupoleva. 2011. № 4. S. 128-135.
14. Goncharenko V.I., Kucherjavenko D.S., Gojjdenko V.K., Skorik N.A. Raspoznavanie tipa avarijjnojj situacii pri ispytanii bespilotnogo kosmicheskogo apparata na osnove ispolzovanija vejjvlet-preobrazovanija // Nejjrokompjutery: razrabotka, primenenie. 2016. № 1. S. 39-48.
15. Patent na izobretenie 2222823 RU. Ustrojjstvo dlja dopuskovogo kontrolja funkcionalnykh sostojanijj tekhnicheskikh sistem / A.I. Polous, A.G. Volkov, A.S. Buryjj. 2002.