OBJECT’S STATE PREDICTION ON THE BASIS OF THE AUTOREGRESSIVE MODEL 

Makarychev Petr Petrovich, Doctor of engineering sciences, professor, head of sub-department of software and computer application, Penza State University (40 Krasnaya street, Penza, Russia), E-mail: makpp@yandex.ru
Afonin Aleksandr Yur'evich, Candidate of engineering sciences, associate professor, sub-department of software and computer application, Penza State University (40 Krasnaya street, Penza, Russia), E-mail: afonin@pnzgu.ru
Shibanov Sergey Vladimirovich, Candidate of engineering sciences, associate professor, sub-department of software and computer application, Penza State University (40 Krasnaya street, Penza, Russia), E-mail: serega@pnzgu.ru 

004.94 

10.21685/2072-3059-2019-2-2 

Background. Identification and forecasting of the state of technical means, social and economic systems is an urgent task. In the article the method of construction of models of identification and forecasting on the basis of theoretical assumptions of the regression analysis and dynamic systems is considered. A distinctive feature of the technique is the representation of the object in the form of a dynamic system with a dedicated feedback, elements of nonlinearity and delay. The concepts of factor and correlation analysis were used to assess the quality of the models.
Results. The substantiation of the structure and parameters of models for solving the problems of identification and forecasting the state of technical objects and socio-economic systems.
Conclusions. The proposed autoregressive model is an effective tool in solving the problems of identification and prediction of the behavior of dynamic objects and socio-economic systems. 

autoregressive model, multiple regression, autoregression, parameter identification, factor and correlation analysis 

1. Radchenko S. G. Matematicheskie mashiny i sistemy [Mathematical machines and systems]. 2013, no. 1, pp. 150–155. [In Russian]
2. Diligenskaya A. N. Identifikatsiya ob"ektov upravleniya [Identification of controlled objects]. Samara: SamGTU, 2009, 136 p. [In Russian]
3. Isermann R., Műnchhof M. Identification of Dynamic Systems. An Introduction with Applications. Darmstadt, Germany: Springer, 2010, 710 p.
4. Cuvorov N. V. Problemy prognozirovaniya [Forecasting problems]. 2005, no. 4, pp. 143–155. [In Russian]
5. Makarychev P. P., Volgina M. A. Modelirovanie mnogokomponentnykh sistem na osnove markirovannykh grafov [Multidimensional system simulation on the basis of marked graphs]. Penza: Izd-vo PGU, 2011, 156 p. [In Russian]
6. Chokoy V. M. Crede Experto: transport, obshchestvo, obrazovanie, yazyk [Crede experto: transport, society, education, language]. 2016, no. 4 (11), pp. 1–11. [In Russian]
7. Krakovskiy Yu. M., Luzgin A. N. Nauka i obrazovanie [Science and education]. 2016, no. 11, pp. 113–126. [In Russian]
8. J. Kumaran @ Kumar, Ravi G. International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering. 2014, vol. 3, iss. 8, pp. 11331–11335.
9. Bates D. M., Watts D. G. Nonlinear Regression Analysis and Its Applications. New York: Wiley, 2007, 392 p. [DjVu, ENG]
10. Montgomery D. C., Peck E. A., G. Geoffrey Vining Introduction to Linear Regression Analysis. 5th Edition. New York: John Wiley & Sons, 2012, 672 p.
11. Mangan N. M., Kutz J. N., Brunton S. L., Proctor J. L. Proceedings of the royal society a. Mathematical, physical and engineering sciences. 2017, no. 8, pp. 1–16.