CORRECT STATISTICAL MODELING IN CONDITIONS OF INCOMPLETE INITIAL INFORMATION

S. G. Radchenko

Abstract


Context. Urgent problem of statistical modeling of the complex systems and processes in conditions of incomplete initial information has been considered.

Objective. The work objective is the use of the method of formalized obtaining of the structure of multifactor statistical model and stable estimation of its coefficient for obtaining highly precise statistical models of elastic deformations of technological system of a lathe.

Methods. When solving applied problems, the analysis of initial data on obtaining statistical models has shown that they are often constructed in conditions of incomplete initial information and the problem which is solved is incorrectly formulated one. In such conditions the model structure obtaining and its stability prove to be the problems in models construction. The author proposes an extended conception of orthogonality of the obtained model: the experiment design, model structure and structure elements of the model are orthogonal. The orthogonal structure of the multifactor statistical model allows obtaining statistically independent estimates of coefficients  of the modeled function. Such a structure may be defined unambiguously with statistically significant coefficients. Normalization of orthogonal effects permits obtaining a maximally stable model structure, and, consequently, its coefficients. The problem will be well-posed.

Results. Application of the considered method of formalized obtaining of the structure of multifactor statistical model and stable estimation of its coefficients is used for obtaining accurate statistical models of elastic deformations of a steel work-piece processed by a lathe. A complete factor experiment has been fulfilled; the factors were as follows: cutting force, work-piece length and diameter, and a response – the value of elastic deformations of the system. Statistical regression moments ˆy1 and  ˆy2  were constructed as the experiment result. In the structure of models the factors are presented by orthogonal contrasts. Statistically significant effects are introduced in the model structure under its formation. The checks of the obtained models by quality criteria have shown their high informativeness, stability, adequacy, statistical efficiency. Using the models on lathes with numerical programmed control allows decreasing the number runs of the cutting tool and, consequently, the time of work-piece processing.

Conclusion. The results of the use of the extended conception of orthogonality and structure of the model of a complete factor experiment, when obtaining the models of elastic deformations of technological system of a lathe, have confirmed the great prospects of application of the considered approach, its effectiveness and expediency in constructing regression statistical models of complex systems and processes.

Keywords


Statistical modeling; ill-posed problems; stable structure of statistical model; extended conception of orthogonality.

References


Voznesenskij V. A., Vy’rovoj V. N., Kersh V. Ya. i dr. pod red. V. A. Voznesenskogo Sovremenny’e metody’ optimizacii compozicionny’x materialov. Kyiv, Budivelnyk, 1983, 144 p.

Noviczkij P. V., Zograf I. A. Izdanie 2, pererabotannoe i dopolnennoe Ocenka pogreshnostej rezultatov izmerenij. Leningrad, Energoatomizdat, 1991, 304 p.

Ajvazyan S. А., Enyukov I. S., Meshalkin L. D., pod red. S. A. Aivazyan. Prikladnaya statistika: Issledovanie zavisimostej: Spravochnoe izdanie. Moscow, Finansy i statistika, 1985, 487 p.

Ajvazyan S. А., Mxitaryan V. S. Pikladnaya statistika. Osnovy ekonometriki: Uchebnik dlya vuzov, v 2 tomax, izdanie 2, ispravlennoe. Vol. 1, Teoriya veroyatnostej i prikladnaya statistika. Moscow, YUNITI-DANA, 2001, 656 p.

Malov S .V. Regressionny’j analiz. Teoreticheskie osnovy i prakticheskie rekomendacii. St.Petersbourg, Izdatelstvo SPbGU, 2013, 280 p.

Hinkelmann K. Kempthorne O. Design and Analysis of Experiments, Introduction to Experimental Design, 2 edition, Vol. 1,Wiley-Interscience, 2007, 631 p. (Wiley Series in Probability and Statistics).

Radchenko S. G. Formalizovanny’e i e’vristicheskie resheniya v regressionnom analize: monografiya. Kyiv, «Kornijchuk», 2015, 236 p.

Konovalova I. O., Berkovich Yu. A., Eroxin A. N. i dr. Optimizaciya svetodiodnoj sistemy’ osveshheniya vitaminnoj kosmicheskoj oranzherei, Aviakosmicheskaya i e’kologicheskaya mediсina, 2016, Vol. 50, No. 3, pp. 17–22.

Radchenko S. G. Metodologiya regressionnogo analiza : monografiya. Kyiv, «Kornijchuk», 2011, 376 p.

Radchenko S. G. Аnаliz metodov modelirovaniya slozhnih sistem, Matematichni mashini i sistemi, 2015, No. 4, pp. 123–127.

Laboratory of experimental statistical method of investigation (LESMI) [Electronic resource]. Access mode: http://www.n-t.org/sp/lesmi

Site of the Department Mechanical Engineering, Mechanical Engineering Institute, National Technical University of Ukraine «Kyiv Polytechnic Institute» [Electronic resource]. Access mode: http://tm-mmi.kpi.ua/index.php/ru/1/publications/


GOST Style Citations


1. Современные методы оптимизации композиционных материалов / [Вознесенский В. А., Выровой В. Н., Керш В. Я. и др.] ; под ред. В. А. Вознесенского. – К. : Будівельник, 1983. – 144 с.

2. Новицкий П. В. Оценка погрешностей результатов измерений / П. В. Новицкий, И. А. Зограф. – 2-е изд., перераб. и доп. – Л. : Энергоатомиздат. Ленингр. отд-ние, 1991. – 304 с.

3. Айвазян С. А. Прикладная статистика : Исследования зависимостей : справ. изд. / С. А. Айвазян, И. С. Енюков, Л. Д. Мешалкин ; под. ред. С. А. Айвазяна. – М. : Финансы и статистика, 1985. – 487 с.

4. Прикладная статистика. Основы эконометрики: Учебник для вузов: В 2 т. 2-е изд. испр. – Т. 1 : Айвазян С. А., Мхитарян В. С. Теория  вероятностей  и  прикладная  статистика. – М. : ЮНИТИ-ДАНА, 2001. – 656 с.

5. Малов С. В. Регрессионный анализ. Теоретические основы и практические рекомендации / С. В. Малов. – Санкт-Петербург : Изд-во СПбГУ, 2013. – 280 с.

6. Hinkelmann K. Design and Analysis of Experiments, Introduction to Experimental Design / Klaus Hinkelmann, Oscar Kempthorne. – 2 edition. – Vol. 1. – Wiley-Interscience, 2007. – 631 p. – (Wiley Series in Probability and Statistics).

7. Радченко С. Г. Формализованные и эвристические решения в регрессионном анализе : монография / Радченко С. Г. – К. : «Корнійчук», 2015. – 236  с.

8. Оптимизация светодиодной системы освещения витаминной космической оранжереи / [Коновалова И. О., Беркович Ю. А., Ерохин А. Н. и др.] // Авиакосмическая и экологическая медицина. – 2016. – Т. 50, № 3. – С. 17–22.

9. Радченко С. Г. Методология регрессионного анализа : монография / С. Г.  Радченко. – К. : «Корнійчук», 2011. – 376 с.

10. Радченко С. Г . Анализ методов моделирования сложных систем / С. Г. Радченко // Математичні машини  і  системи. – 2015. – № 4. – С. 123–127.

11. Лаборатория экспериментально-статистических методов исследований (ЛЭСМИ). – [Электронный ресурс]. – Режим доступа: http://www.n-t.org/sp/lesmi

12. Сайт кафедры «Технология машиностроения» Механико-машиностроительного института Национального технического университета Украины «Киевский политехнический институт». – [Электронный  ресурс]. – Режим доступа: http://tmmmi.kpi.ua/index.php/ru/1/publications/




DOI: https://doi.org/10.15588/1607-3274-2017-4-6



Copyright (c) 2018 S. G. Radchenko

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Address of the journal editorial office:
Editorial office of the journal «Radio Electronics, Computer Science, Control»,
Zaporizhzhya National Technical University, 
Zhukovskiy street, 64, Zaporizhzhya, 69063, Ukraine. 
Telephone: +38-061-769-82-96 – the Editing and Publishing Department.
E-mail: rvv@zntu.edu.ua

The reference to the journal is obligatory in the cases of complete or partial use of its materials.