AN ADAPTIVE NETWORK BASED FUZZY INFERENCE (ANFIS) MODEL TO PREDICT THE GLAZE COMPOSITIONS AND GLASSING VALUES IN CERAMIC GLAZE APPLICATIONS
Ugur Kut, Iskender Isik, Eyyup Gulbandilar
Pagini: 291-297
Publicat: 31 May 2015
Vizualizări: 3,493
Descărcări: 787
Rezumat: In this study, it is aimed to predict the glazing and appropriate glaze composition with computer software to reduce of the product costs during prototype production in the ceramic industry. Hence, formulas were prepared to use washed Uşak Kaolin, Minium and Quartz. Samples were prepared using these formulas and fired at deformation temperatures 950 and 1150 0C. An adaptive network based fuzzy inference (ANFIS) model to predict the glaze compositions and glassing values were chosen as output values while temperature, surface tension and expansion coefficient were chosen as input values. To this end, MatLab 2010 Toolbox package program was used in this study. A comparative evaluation of the predicted and experimental results has shown that ANFIS model has a high accuracy and absolute relative error is less than 17.39%. As a result of training, high performance was obtained between regression for glaze components R2=0.5301and R2=0.9984. Likewise, according to test results, high performance was obtained between regression for glassing R2=0.8167 and regressions for glaze components R2=0.9996 and 0.9986. Moreover, the ANFIS model was an easy and practical method to predict the glaze compositions and glassing values.
Cuvinte cheie: artificial neuronal network, an adaptive network based fuzzy inference, ceramic, chemical properties, glazing, glaze component
Citează acest articol: Ugur Kut, Iskender Isik, Eyyup Gulbandilar. AN ADAPTIVE NETWORK BASED FUZZY INFERENCE (ANFIS) MODEL TO PREDICT THE GLAZE COMPOSITIONS AND GLASSING VALUES IN CERAMIC GLAZE APPLICATIONS. Journal of International Scientific Publications: Materials, Methods & Technologies 9, 291-297 (2015). https://www.scientific-publications.net/en/article/1000776/
Înapoi la cuprinsul volumului
© 2025 The Author(s). This is an open access article distributed under the terms of the
Creative Commons Attribution License https://creativecommons.org/licenses/by/4.0/, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. This permission does not cover any third party copyrighted material which may appear in the work requested.
Disclaimer: The Publisher and/or the editor(s) are not responsible for the statements, opinions, and data contained in any published works. These are solely the views of the individual author(s) and contributor(s). The Publisher and/or the editor(s) disclaim any liability for injury to individuals or property arising from the ideas, methods, instructions, or products mentioned in the content.
