Моделирование нестационарных временных рядов технологических параметров с помощью метода «Гусеница»

Z. J. Vorotnikova

doi:10.31498/2225-6733.30.2015.52743

Authors

Z. J. Vorotnikova State higher educational establishment "Priazovskyi state technical university", Mariupol, Ukraine

DOI:

https://doi.org/10.31498/2225-6733.30.2015.52743

Keywords:

non-stationary temporal row, structure of temporal row, singular spectrology, main components

Abstract

Information on the existing methods of non-stationary temporal rows modelling and a method of automatic design of non-stationary temporal rows of technological parameters worked out by the author by SSA method and its further use to analyze the technological process have been presented in the article. The task of researches is to develop such an algorithm that would make it possible to carry out automatic design of non-stationary temporal rows of technological parameters as data from comptrollers arrive and are being stored in CAS server database to be used to analyze the technological process next. The fulfilled analysis of existing methods of non-stationary rows of technological parameters design showed that presently there no theoretical base making it possible to make up such models. The algorithm of automatic modeling and a method of non-stationary temporal rows of technological parameters models storing with the purpose to use them in the imitation and expert systems for further analysis of technological process have been offered. The design method used in the process means additive presentation of temporal rows, where a row can be presented as combination of two sets of different in their nature components. In the article correlation of maximal amount of stationary and non-stationary submodels is presented for 26 parameters (for 180 segments), design quality, and statistical parameters of noise

Author Biography

Z. J. Vorotnikova, State higher educational establishment "Priazovskyi state technical university", Mariupol

Кандидат технических наук, доцент

References

Уилкс С. Математическая статистика: пер. с англ. / С. Уилкс. – М.: Наука, 1967. – 632 с.

Орлов Ю.Н. Нестационарные временные ряды: Методы прогнозирования с примерами анализа финансовых и сырьевых рынков / Ю.Н. Орлов, К.П. Осминин. – М.: URSS, 2011. – 384 с.

Канторович Г.Г. Лекции: Анализ временных рядов / Г.Г. Канторович // Экономический журнал / ГУ ВШЭ. – M., 2002. – Т. 6, №2. – C.251-273.

Лукашин Ю.П. Адаптивные методы краткосрочного прогнозирования временных ря-дов: учебное пособие / Ю.П. Лукашин. – М.: Финансы и статистика, 2003. – 416 с.

Маала С. Вейвлеты в обработке сигналов / С. Маала. – М. : Мир, 2005. – 671 с.

Воротникова З.Е. Моделирование временных рядов технологических параметров / З.Е. Воротникова // Вісник Приазовського державного технічного університету : Зб. наук. пр. / ДВНЗ «ПДТУ». – Маріуполь, 2013. – Вип. 27. – С. 197-204.

Mann H.B. On a test of whether one of two random variables is stochastically larger than the other / H.B. Mann, D.R. Whitney // Annals of Mathematical Statistics. – 1947. – № 18. – P. 50-60.

Golyandina. N.E. Analysisof Time Series Structure: SSA and Related Techniques / N.E. Go-lyandina, V.V. Nekrutkin, A.A. Zhigljavsky. – Chapman & Hall, 2001. – 305 P.

Box, G.E.P. A note on the generation of random normal deviates // Annals of mathematical statistics. – 1958. – 29, №2. – P. 610-611.

Раскин Л.Г. Математическое моделирование функционирования сложных систем / Л.Г. Раскин. – Х. : ВИТРА ПВО, 1988. – 178 с.

Frosini B.V. On the distribution and power of goodness-of-fit statistic with parametric and nonparametric applications, «Goodness-of-fit» / Frank E. Grubbs; ed. By Revesz P., Sarkadi K., Sen P.K. – Amsterdam-Oxford-New York: North Holland Publ. Comp, 1987. – P. 133-154.