The neural network approximation to the size effect in fracture of cementitious materials

Arslan A., Ince R.

ENGINEERING FRACTURE MECHANICS, vol.54, no.2, pp.249-261, 1996 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 54 Issue: 2
  • Publication Date: 1996
  • Doi Number: 10.1016/0013-7944(95)00140-9
  • Journal Name: ENGINEERING FRACTURE MECHANICS
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.249-261
  • Gazi University Affiliated: No

Abstract

Modeling of material behavior generally involves the development of a mathematical model derived from observations and experimental data. An alternative way discussed in this paper, is neural network-based modeling that is a subfield of artificial intelligence. The main benefit in using a neural network approach is that the network is built directly from experimental data using the self-organising capabilities of the neural network. In this paper, size effects in fracture of cementitious materials are modeled with a back-propagation neural network. The results of neural network-based size effect law look viable and very promising. Copyright (C) 1996 Elsevier Science Ltd.