DOI: https://doi.org/10.31319/2519-8106.2(43)2020.219266

THE USE OF FUZZY CLUSTERING IN SOLVING PROBLEM IN PREDICTING THE DURABILITY OF CORROSIVE STRUCTURES

Лариса Іванівна Коротка

Анотація


In solving the problems of forecasting corroding structures, the problematic aspects related to computational costs are considered. It is proposed to use a multi-stage approach to reduce computational costs in solving tasks of this class. In particular: a fuzzy clustering algorithm is used for processing multivariate data; the resulting clusters are used to build the rule base; and the fuzzy logical output of the Mamdani type is used for defasification.

Ключові слова


fuzzy clustering; fuzzy knowledge base; fuzzy inference; corrosive structures

Повний текст:

PDF (English)

Посилання


Chuen-Chien Lee (1990) Fuzzy Logic in Control Systems: Fuzzy Logic Controller, Part I1. IEEE Transactions on systems, man, and cybernetics. 1990/3. – Vol. 20, № 2. – P. 404–418.

Egorov A.V., Kuprijanova N.I. (2010) Osobennosti metodov klasterizaciju. [Features of clustering methods] Izvestija JuFU. Tehnicheskie naukiju Tematicheskij vypusk. S. 174–178. (in Russian).

Harmider L.D. , Taranenko I.V., Korotka L.I., Begma P.O. (2019) Methodological approach to labor potential assessment based on the use of fuzzy sets theory Naukovyi Visnyk Natsionalnoho Hirnychoho Universytetu. № 6 – 2019. 144–149 p. http://dx.doi.org/10.29202/nvngu/2019-6/21

Korotkaya L. I. (2018) Algoritm polucheniya uchebnyih obraztsov dlya neyronnoy seti pri reshenii zadach dolgovechnosti korrodiruyuschih konstruktsiy [Algorithm for obtaining training samples for a neural network in solving problems of predicting the durability of design that are subject to corrosion] // Computer modeling: analysis, control, optimization. – № 1(3). – P. 8–25. (in Russian). http://dx.doi.org/10.32434/2521-6406-2018-3-1

Korotka L. I, Zelentsov D. G. Method of solving optimal design problems based on flexible tolerance strategy International Journal of Mathematical Modelling and Numerical Optimisation, 2020 Vol.10 No.3 – pp. 255–269. (DOI: 10.1504/IJMMNO.2020.108613)

Korotka L.I., Korotka Y. A. (2017) The use of elements of computational intelligence in problems of forecasting of corroding constructions durability. Mathematical and computer modelling. Series: Technical sciences. – Issue 16. – P. 64–71.

Kosko B. (1994) Fuzzy Systems as Universal Approximators. IEEE Trans. on Computers. Vol. 43. №11. P.1329–1333.

Lee J, Kim T. A messy genetic algorithm and its application to an approximate optimization of an occupant safety system. Journal of Automobile Engineering. 2009;757–758.

Monyei CG, Aiyelari T, Oluwatunde S. Neural Network Modeling of Electronic Waste Deposits in Nigeria: Subtle Prod for quick Intervention’ in proceedings of the iSTEAMS Research. Nexus Multidisciplinary Conference. 2013; 1(4):181–188.

Nicholas Ali, Kumaran Behdinan, Zouheir Fawaz, “Applicability and Viability of a GA based Finite Element Analysis Architecture for Structural Design Optimization,” Computers and Structures, 81, 2259–2271, 2003.

Ovchinnikov I.G. Matematicheskie modeli korrozionnogo iznosa nezaschischennyih metallicheskih konstruktsiy [Mathematical models of corrosive wear of unprotected metal constructions] / I.G. Ovchinnikov, I.I. Ovchinnikov // Promyishlennyie pokryitiya. 2014. Vyip. №№9-10. S. 76–79. (in Russian).

Piegat Andrzej (2001) Fuzzy Modeling and Control: with 96 tables / Andrzej Piegat. – Heidelberg: New York: Physica-Verl. 728 p.

Pochtman Yuriy Optimal design of pressure vessels including the effect of environment / Pochtman Yuriy M., Fridman Mark M. // Computer Assisted Mechanics and Engineering Sciences 1995.

Shtovba S.D., Galuschak A.V. (2016) Kriteriyi navchannya nechitkogo klasifikatora na osnovi vidstani mizh golovnimi konkurentami [Fuzzy classifier learning based on distance between the main competitors]. Radio Electronics, Computer Science, Control. – № 2. – P. 70–76. (in Ukrainian)

Shtovba S. Ensuring accuracy and transparency of Mamdani fuzzy model in learning by experimental data / S. Shtovba // Journal of Automation and Information Sciences. – 2007. – Vol. 39, № 8. – P. 39–52.

Shtovba S. Analyzing the criteria for fuzzy classifier learning / S. Shtovba, O. Pankevich, A. Nagorna // Automatic Control andComputer Sciences. – 2015. – Vol. 49, № 3. – P. 123–132

Solodka N.A., Shapovalov D.D. (2019) Analiz i obrabotka dannyh kompanii kak sposob povyshenija ee pribyl'nosti [Analysis and processing of company data as a method of profitability improving]. Elektronnij naukovo-praktichnij zhurnal «Shіdna Єvropa: ekonomіka, bіznes ta upravlіnnja» – № 6 (23) – S. 756–760 (in Russian).

Us S.A., Korjashkina L.S. Modeli ta metody pryjnjattja rishen' (druge vydannja) [Models and methods of decision making] // Dnipropetrovs'k, NGU, 2018, 270 s.

Zadeh Lotfi A. (1975) The concept of a linguistic variable and its application to approximate reasoning. / Lotfi A. Zadeh // Part 1 Information Sciences. 8(3), Р. 199–249.

Zelentsov, D., Denysiuk, O. (2019) Neural Network Algorithm for Accuracy Control in Modelling of Structures with Changing Characteristics. In: Hu Z., Petoukhov S., Dychka I., He M. (eds) Advances in Computer Science for Engineering and Education. ICCSEEA 2018. Advances in Intelligent Systems and Computing, vol 754. Springer.

Zelentsov D. G., Korotkaya L. I. (2018) Tehnologii vyichislitelnogo intellekta v zadachah modelirovaniya dinamicheskih sistem: monografiya. [Technologies of computational intelligence in tasks of dynamic systems modeling: monograph] / D. G. Zelentsov, L. I. Korotkaya // – Dnepr: Balans-Klub. – 178 p. (in Russian). (http://dx.doi.org/10.32434/mono-1-ZDG-KLI)

Chuen-Chien Lee Fuzzy Logic in Control Systems: Fuzzy Logic Controller, Part IІ. IEEE Transactions on systems, man, and cybernetics. 1990/3. Vol. 20, № 2. P. 404–418.

Егоров А .В., Куприянова Н. И. Особенности методов кластеризации. Известия ЮФУ. Технические науки. 2010.Тематический выпуск. С. 174–178.

Harmider L. D. , Taranenko I. V., Korotka L. I., Begma P. O. Methodological approach to labor potential assessment based on the use of fuzzy sets theory. Naukovyi Visnyk Natsionalnoho Hirnychoho Universytetu. 2019. № 6. P. 144–149. (DOI: http://dx.doi.org/10.29202/nvngu/2019-6/21)

Короткая Л.И. Алгоритм получения учебных образцов для нейронной сети при решении задач долговечности корродирующих конструкций. Компьютерное моделирование: анализ, управление, оптимизация. 2018. № 1(3). С. 8–25. (DOI: http://dx.doi.org/10.32434/2521-6406-2018-3-1)

Korotka L. I, Zelentsov D. G. Method of solving optimal design problems based on flexible tolerance strategy. International Journal of Mathematical Modelling and Numerical Optimisation. 2020. Vol.10. No.3 P. 255–269. (DOI: http://dx.doi.org/10.1504/IJMMNO.2020.108613)

Korotka L. I., Korotka Y. A. The use of elements of computational intelligence in problems of forecasting of corroding constructions durability. Mathematical and computer modelling. Series: Technical sciences. 2017. Issue 16. P. 64–71.

Kosko B. Fuzzy Systems as Universal Approximators. IEEE Trans. on Computers. 1994. Vol. 43. №11. P. 1329–1333.

Lee J, Kim T. A messy genetic algorithm and its application to an approximate optimization of an occupant safety system. Journal of Automobile Engineering. 2009. P. 757–758.

Monyei CG., Aiyelari T., Oluwatunde S. Neural Network Modeling of Electronic Waste Deposits in Nigeria: Subtle Prod for quick Intervention’ in proceedings of the iSTEAMS Research. Nexus Multidisciplinary Conference. 2013. № 1(4). P. 181–188.

Nicholas Ali, Kumaran Behdinan, Zouheir Fawaz Applicability and Viability of a GA based Finite Element Analysis Architecture for Structural Design Optimization. Computers and Structures. 2003. № 81, P. 2259–2271.

Овчинников И.Г., Овчинников И.И. Математические модели коррозионного износа незащищенных металлических конструкций. Промышленные покрытия. 2014. Вып. №№9–10. С. 76–79.

Piegat Andrzej Fuzzy Modeling and Control. Heidelberg: New York: Physica-Verl. 2001. 728 p.

Pochtman Yuriy, Fridman Mark M. Optimal design of pressure vessels including the effect of environment Computer Assisted Mechanics and Engineering Sciences. 1995.

Штовба С.Д., Галущак А.В. Критерії навчання нечіткого класифікатора на основі відстані між головними конкурентами. Радіоелектроніка, інформатика, управління. 2016. № 2. С. 70–76.

Shtovba S. Ensuring accuracy and transparency of Mamdani fuzzy model in learning by experimental data. Journal of Automation and Information Sciences. 2007. Vol. 39, № 8.

P. 39–52.

Shtovba S., Pankevich O., Nagorna A. Analyzing the criteria for fuzzy classifier learning. Automatic Control andComputer Sciences. 2015. Vol. 49, № 3. P. 123–132.

Солодкая Н. А., Шаповалов Д. Д. Анализ и обработка данных компании как способ повышения ее прибыльности. Електронний науково-практичний журнал «Східна Європа: економіка, бізнес та управління». 2019. № 6 (23). С. 756–760

Ус С. А., Коряшкіна Л. С. Моделі та методи прийняття рішень (друге видання). Дніпропетровськ: НГУ, 2018. 270 с.

Zadeh Lotfi A. The concept of a linguistic variable and its application to approximate reasoning. Part 1 Information Sciences. 1975. 8(3). Р. 199–249.

Zelentsov D., Denysiuk O. Neural Network Algorithm for Accuracy Control in Modelling of Structures with Changing Characteristics. Advances in Computer Science for Engineering and Education. ICCSEEA 2018. Advances in Intelligent Systems and Computing: In: Hu Z., Petoukhov S., Dychka I., He M. (eds). 2019. vol. 754. P. 507–516. (Springer)

Зеленцов Д. Г., Короткая Л. И. Технологии вычислительного интеллекта в задачах моделирования динамических систем. Днепр: Баланс-клуб, 2018. 178. (DOI: http://dx.doi.org/10.32434/mono-1-ZDG-KLI)




Текст

ISSN 2519-8106 (Print), eISSN 2519-8114 (Online)