Title:
Artificial Intelligence Model for Early-Age Autogenous Shrinkage of Concrete
Author(s):
Moncef L. Nehdi and Ahmed M. Soliman
Publication:
Materials Journal
Volume:
109
Issue:
3
Appears on pages(s):
353-362
Keywords:
artificial neural network; autogenous; database; early age; modeling; shrinkage.
DOI:
10.14359/51683826
Date:
5/1/2012
Abstract:
In this paper, an artificial neural network (ANN) model for the early-age autogenous shrinkage of concrete is proposed. The model inputs include the cement content, water-cement ratio (w/c), type and percentage of supplementary cementitious materials, total aggregate volume, curing temperature, and hydration age. The autogenous shrinkage of concrete is the model output. The autogenous shrinkage database assembled and used in the training of the proposed ANN is considered a contribution to the state of the art of knowledge; it includes testing results on modern concretes under various environmental conditions. The developed ANN model exhibited excellent capability in capturing complex effects and interactions among model inputs on the development of autogenous shrinkage. Subsequent to model validation, a parametric study was carried out to identify the effects of input variables on the evolution of autogenous shrinkage. The trained ANN model demonstrated the ability of predicting the autogenous shrinkage behavior, not only of traditional concrete mixtures, but also that of modern concrete mixtures such as reactive powder concrete, which are characterized by very low w/c.