Complex estimation, identification and prediction of difficult nonlinear processes
- Details
- Category: Information technologies, systems analysis and administration
- Last Updated on 21 July 2014
- Published on 24 December 2013
- Hits: 4039
Authors:
V.I. Korniienko, Dr. Sci. (Tech.), Professor, State Higher Educational Institution “National Mining University”, Senior Lecturer of the Department of Information Security and Telecommunications, Dnipropetrovsk, Ukraine.
I.G. Gulina, State Higher Educational Institution “National Mining University”, Postgraduate Student, Assistant Lecturer of the Department of Information Security and Telecommunications, Dnipropetrovsk, Ukraine.
L.V. Budkova, State Higher Educational Institution “National Mining University”, Postgraduate Student, Department of Information Security and Telecommunications, Dnipropetrovsk, Ukraine.
Abstract:
Purpose. To increase the accuracy of dynamic models of difficult nonlinear processes for solving tasks to control these processes.
Methodology. Complex estimation of characteristics, the choice of model structure and parametric identification of difficult nonlinear processes on the example of technological processes of mining and metallurgical production and processes in information networks.
Findings. We have developed the prediction models of process indices of the ore ragging and the thermal state of blast-furnace process as well as traffic fractal models in information networks. The relative errors of approximation and prediction on the models range from 3 to 4.6%. The adequacy of experimental and model data has been proved.
Originality. We have proposed the complex method of estimation and identification of difficult nonlinear processes comprising the estimation of characteristics based on the complex use of time-frequency, statistical and fractal analyses, the choice of model structure in accordance with received qualitative and numerical values of the process characteristics and its parametric identification based on the methods of local or global optimization allowing to get adequate models of the processes having increased accuracy.
Practical value. The results can be applied to design management algorithms of complex nonlinear processes based on their comprehensive evaluation and identification.
References:
1. Кузнецов С.П. Динамический хаос / Кузнецов С.П. – М.: Физматлит, 2002. – 296 с.
Kuznetsov, S.P. (2002), Dinamicheskiy khaos [Dynamic Chaos], Fizmatlit, Moscow, Russia.
2. Шустер Г.Г. Детерминированный хаос. Введение / Шустер Г.Г. [Пер. с англ.] – М.: Мир, 2004. – 256 с.
Schuster, G.G. (2004), Determinirivannyi khaos. Vvedeniye [Deterministic Chaos. Introduction], Mir, Moscow, Russia.
3. Федер Е. Фракталы / Федер Е. [Пер. с англ.] – М.: Мир, 1991.– 254 с.
Feder, J. (1991), Fraktaly [Fractals], Mir, Moscow, Russia.
4. Шелухин О.И. Мультифракталы. Инфокоммуникационные приложения / Шелухин О.И. – М.: Горячая линия – Телеком, 2011. – 576 с.
Shelukhin, O.I. (2011), Multifraktaly. Infokommunikatsyonnye prilozheniya [Multifractals. Infocommunication applications], Goryachaya Linia, Moscow, Russia.
5. Кузнецов Г.В. Композиційна структурно-параметрична ідентифікація нелінійних динамічних об’єктів керування / Г.В. Кузнецов, В.І. Корнієнко, О.В. Герасіна // Наукові вісті НТУУ КПІ. – 2009. – № 5. – С. 69–75.
Kuznetsov, G.V., Korniienko, V.I. and Gerasina, O.V. (2009), “Composition strucrural-parametric identification of nonlinear dynamic controlled objects”, Naukovi visti NTUU “KPI”, no. 5, pp. 69–75, Ukraine.
6. Riedi, R.H., Crouse, M.S., Ribeiro, V. and Baraniuk R.G. (1999), “A multifractal wavelet model with application to network traffic”, IEEE Transactions on Information Theory, vol. 45, pp. 992–1018.
7. Crovella, M.E. and Bestravos, A. (1997), “Self-similarity in World Wide Web traffic: Evidence and possible causes”, IEEE Transactions on Networking, vol. 5, no. 6, pp. 835–836.
8. Архів трафіку [Електронний ресурс] – Режим доступу: http://ita.ee.lbl.gov.
Traffic archive: http://ita.ee.lbl.gov.
![]() ![]() |
|
![]() ![]() ![]() |
![]() |