Dubenko Yuriy Vladimirovich, Candidate of engineering sciences, associate professor, sub-department of informatics and computer science, Institute of Computer Systems and Information Security, Kuban State Technological University (135 Krasnaya street, Krasnodar, Russia), E-mail: email@example.com
Dyshkant Evgeniy Evgen'evich, Senior lecturer, sub-department of internal electrical equipment and automation, Armavir Mechanical and Technological Institute (branch) of Kuban State Technological University (127 Kirova street, Armavir, Russia), E-mail: firstname.lastname@example.org
Background. The object of the study is systems for determining optimal methods for predicting the parameters of complex technical systems. The goal of the work is to develop a system for determining optimal methods for predicting the parameters of complex technical systems.
Materials and methods. In the course of the research there was carried out an analysis of the sources devoted to the problem of determining the best methods for predicting the parameters of complex technical systems, which showed a low degree of elaboration. The development of a system for determining optimal methods for predicting the parameters of complex technical systems was carried out using a fuzzy logic apparatus and a method for analyzing precedents.
Results. A system for determining the optimal methods for predicting the parameters of complex technical systems has been developed.
Conclusions. The application of the developed system as part of the prediction blocks, which are components of the control systems of complex technical systems, will improve their performance due to the possibility of determining a limited group of the most optimal methods, as well as reliability due to the use of methods allowing to obtain the most accurate forecast with a high degree of probability.
1. Simankov V. S., Buchatskaya V. V. Vestnik Adygeyskogo gosudarstvennogo universiteta. Ser. 4, Estestvenno-matematicheskie i tekhnicheskie nauki [Bulletin of Adygei State University. Series 4, Natural, mathematical and engineering sciences]. 2012, no. 2, pp. 118–123.
2. Shorikov A. F., Butsenko E. V. Izvestiya Ural'skogo gosudarstvennogo ekonomicheskogo universiteta [Proceedings of Ural State Economic University]. 2006, no. 5 (17), pp. 183–191.
3. Petrichenko G. S., Kritskaya L. M., Naryzhnaya N. Yu. Politematicheskiy setevoy elektronnyy nauchnyy zhurnal Kubanskogo gosudarstvennogo agrarnogo universiteta [Multitopical online scientific journal of Juban State Agrarian University]. 2005, no. 14, pp. 1–5.
4. Larichev O. I. Verbal'nyy analiz resheniy [Verbal analysis of solutions]. Institute for Systems Analysis of RAS. Moscow: Nauka, 2006, 181 p.
5. Dubenko Yu. V., Dyshkant E. E. Razrabotka matematicheskoy modeli mnogofaktornogo nechet-kogo prognozirovaniya poter' elektroenergii: monografiya [Development of a mathematical model of multifactory fuzzy forecasting of electrical energy losses: monograph]. Krasnodar: Izd-vo FGBOU VPO «KubGTU», 2016, 120 p.
6. Rutkovskaya D., Pilin'skiy M., Rutkovskiy L. Neyronnye seti, geneticheskie algoritmy i nechetkie sistemy [Neural networks, genetic algorithms and fuzzy systems]. Transl. from Polish by I. D. Rudinskiy. Moscow: Goryachaya liniya – Telekom, 2006, 452 p.
7. Vagin V. N., Golovina E. Yu., Zagoryanskaya A. A., Fomina M. V. Dostovernyy i pravdopodobnyy vyvod v intellektual'nykh sistemakh [Reliable and credible conclusions in intelligence systems]. Moscow: Fizmatlit, 2008, 704 p.
8. Varshavskiy P. R., Eremeev A. P. Iskusstvennyy intellekt i prinyatie resheniy [Artificial intelligence and decision making]. 2009, no. 2, pp. 45–57.
9. Gmurman V. E. Teoriya veroyatnostey i matematicheskaya statistika: ucheb. posobie [The probability theory and mathematical statistics: teaching aid]. 12th ed. rev. Moscow: Vysshee obrazovanie, 2008, 479 p.
10. UCI Machine Learning Repository: Data Set. Available at: http://archive.ics.uci.edu/ml/datasets/Combined+Cycle+Power+Plant