А. V. Nosovskyi, G. L Sharaevsky, N. М. Fialko, L G. Sharaevsky, L. B. Zimin
Institute for Safety Problems of Nuclear Power Plants, NAS of Ukraine,
12, Lysogirska st., Kyiv, 03028, Ukraine
In order to improve the operational safety of nuclear power plants (NPP) and the support systems for operating personnel ofnudear power units and to exclude possible errors due to human factors, as part of the developed automatic systems for operating diagnostics of the current technical conditions of the main equipment (in particular, the main agregate modes of the main aggregate circulation pumps), an additional subsystem for the trend of changes in this state was created. This subsystem is designed to enable the early detections of latent initial phases of potentially dangerous violations of the normal course of physical processes in the most vulnerable modes of pumping units and the timely prevention of the development of identified deviations and anomalies in emergency situations. As it is known the essence of the problem consists of that up-to-date NPP monitoring-and-control systems being the part of NPP computer-aided manufacturing control systems (CAMCS) have in their base a deterministic approach to logistic analysis of equipment operating conditions to prevent controlled by them parameters from the falling outside preliminary sate safe limits. In this work the approach to building SOM-neural networks regarding the tasks of accidental objects recognition is reviewed. Modified algorithm of study in the recognizing SOM-neural structure is proposed in condition of absence of a priori information on the power of classes multitude to-be-recognized. In this article the approach to the training and automated adaptation of diagnostic in conditions of a priory uncertainty of many classes to be recognized is proposed. This approach is implemented on the basis of determination of the moment of disorder of random time series using the auto-regressive model. In this work the approach to the training and automated adaptation of diagnostic neuro-networking structure on the basis of Kohonen’s topology in conditions of a priors uncertainty of many classes to be recognized is proposed. This approach is implemented on the basis of determination of the moment of disorder of random time series using autoregressive model.
Keywords: NPP primary circulation pumps, artificial neural networks, self-organizing map, learning algorithm, stochastic systems, self adaptive, automatic diagnostic.
1. Nosovskyi A. V., Sharaevskyi G. I., Fialko N. M., Shar-aevsky I. G., Zimin L. B. (2019). [Physical substantiation of the mechanical sealing systems automatic diagnostics problem of NPP coolant reactor pumps]. Yaderna enerhety-ka ta dovkillya [Nuclear power and the environment], vol. 15, no. 3, pp. 26-35. (in Ukr.)
2. Sharaevskyi G. I., Fialko N. M., Sharaevskyi I. G., Zimin L. B. (2019). [Statistical model and generalized cri-
terion for estimation of the current technical state of the main circulation pumps of the first circuit of VVER reactors]. Tekhnologicheskie sistemy [Technological Systems], vol. 86/1, pp. 60-69. (in Ukr.)
3. Sharaevsky G. І., Fialko N. М., Sharaevsky І. G., Zimin L. B. (2019). [Computer model of short-term forecast of the trend dynamics of technical state of the NPP main circulation pumps]. Tekhnologicheskie sistemy [Technological Systems], vol. 87/2, pp. 54-60. (in Ukr.)
4. Fomin Ya. A, Tarlovsky G. R. (1986). Statisticheskaja teori-ja raspoznavanija obrazov [Statistical Pattern Recognition Theory]. Moscow: Radio i svyaz, 264 p. (in Russ.)
5. Uossermen F. (1992). Nejrokomputernaya tekhnika: Teorija i praktika [Neurocomputer Technology: Theory and Practice]. Moscow: Mir, 240 p. (in Russ.)
6. Kohonen T. (2006). Self-Organizing Map. Springler Verlag, 665 p.
7. Sharaevskyi G. І., Shapovalova S. I. (2010). Algoritm struk-turizatsii karty samoorganizatsii pri obuchenii neironnoi seti [The self-organization map structuring algorithm for training a neural network]. Proceedings of the Х Int. Conf. “Intelligent Information Analysis IAI2010” (Ку/iv, Mаy 18-21, 2010). Kyiv: Prosvita, 2010, pp. 434-438. (in Russ.)
8. Zhigalevsky А. А., Krasnovsky А. Е. (1988). Obnaruzhenie razladki sluchajnykh protsessov v zadachakh radiotekhni-ki [Detection of random processes in radio engineering problems]. Leningrad: Leningrad University Publ., 224 p. (in Russ.)
9. Bulinsky А. V., Shiriaev A. V. (2005). Teorija sluchajnykh protsessov [Theory of random processes]. Moscow: Fizmat-lit, 408 p.
10. Korolyuk V. S., Portenko N. I., Skorokhod A. V., Turbin A. F. (1985). Spravochnik po teorii vemyatnostej i matematich-eskoj statistike [Handbook of Probability Theory and Mathematical Statistics]. Moscow: Nauka, 640 p. (in Russ.)
11. Kliuchnikov А. А., Sharaevskyi I. G., Fialko N. M., Zimin L. B., Sharaevskyi G. I. (2010). Teplofizika bezopasn-jsti atomnykh elektrostancij [Thermophysics of NPP safety]. Kyiv: ISP NPP, NAS of Ukraine, 484 p. (in Russ.)
12. Kliuchnikov А. А., Sharaevsky I. G., Fialko N. M., Zimin L. B., Sharaevskaya N. I. (2013). Teplofizika povre-zhdenij reaktornykh ustanovok [Thermophysics of NPP damages]. Kyiv: ISP NPP, NAS of Ukraine, 528 p. (in Russ.)
If the article is accepted for publication in the journal «Industrial Heat Engineering» the author must sign an agreement on transfer of copyright. The agreement is sent to the postal (original) or e-mail address (scanned copy) of the journal editions.
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License International CC-BY that allows others to share the work with an acknowledgement of the work’s authorship and initial publication in this journal.