Artificial neural network application on microstructure-compressive strength relationship of cement mortar

ÖNAL O., Ozturk A. U.

ADVANCES IN ENGINEERING SOFTWARE, cilt.41, sa.2, ss.165-169, 2010 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 41 Sayı: 2
  • Basım Tarihi: 2010
  • Doi Numarası: 10.1016/j.advengsoft.2009.09.004
  • Dergi Adı: ADVANCES IN ENGINEERING SOFTWARE
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.165-169
  • Anahtar Kelimeler: Mortar, Backscattered electron imaging, Microstructure, Compressive strength, Artificial neural network, IMAGE-ANALYSIS, PREDICTION, CONCRETE, PASTE
  • Dokuz Eylül Üniversitesi Adresli: Evet

Özet

Artificial neural network analysis was performed to establish a relationship between microstructural characteristics and compressive strength values of cement mortar in this study. Pore properties such as pore area ratio, total pore length, total dendrite length and average roundness, and paste properties such as hydrated part area and unhydrated part area ratios were approached as microstructural characteristics obtained by digital image analysis. These microstructural quantities were correlated with compressive strength values of cement mortar incorporating with the chemical admixtures by different dosages, which resulted as several microstructural characteristics. Artificial neural network (ANN) analysis indicated that by using ANN as non-linear statistical data modeling tool, a strong correlation between the microstructural properties of cement mortar and compressive strengths can be established. (C) 2009 Elsevier Ltd. All rights reserved.