Please use this identifier to cite or link to this item:
Title: Estimation of mechanical properties of limestone using regression analyses and ANN
Other Titles: Estymacja mechanicznych wlasciwosci wapienia przy zastosowaniu analizy regresji i sztucznych sieci neuronowych
Authors: Teomete, Egemen
Tayfur, Gökmen
Aktaş, Engin
Keywords: Artificial neural networks
Regression analysis
Issue Date: 2012
Publisher: Foundation Cement, Lime, Concrete
Source: Teomete, E., Tayfur, G., and Aktaş, E. (2012). Estimation of mechanical properties of limestone using regression analyses and ANN. Cement, Wapno, Beton, (6), 373-389.
Abstract: Estimation of mechanical properties of rocks is important for researchers and field engineers working in cement and concrete industry. Limestone is used in cement production. In this study, Schmidt hammer, ultrasonic pulse velocity, porosity, uniaxial compression and indirect tension tests were conducted on limestone obtained from a historical structure. Regression analyses were used to develop models relating mechanical properties of limestone. Artificial Neural Network (ANN) was performed to determine the mechanical properties. The performance of regression models and ANN were compared by existing models in the literature. The results showed that the regression models and ANN yield satisfactory performance with minimum error. The regression models between tensile strength and wave velocity, tensile strength and porosity, wave velocity and porosity have been developed for the first time in literature. The ANN is used for the first time to estimate the mechanical properties of limestone. The use of separate training and testing sets in the regression analyses of mechanical properties of limestone is conducted for the first time. The models developed in this study can be used by researchers and field engineers to relate the mechanical properties of limestone.
ISSN: 1425-8129
Appears in Collections:Civil Engineering / İnşaat Mühendisliği
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection

Files in This Item:
File Description SizeFormat 
6801.pdfMakale9.15 MBAdobe PDFThumbnail
Show full item record

CORE Recommender


checked on Dec 9, 2023

Page view(s)

checked on Dec 4, 2023


checked on Dec 4, 2023

Google ScholarTM


Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.