Title: Predicting Performance of Self-Compacting Concrete Mixtures Using Artificial Neural Networks

Author(s): Moncef Nehdi, Hassan El Chabib, and M. Hesham El Naggar

Publication: Materials Journal

Volume: 98

Issue: 5

Appears on pages(s): 394-401

Keywords: compressive strength; models; self-compacting concrete; slump flow

DOI: 10.14359/10729

Date: 9/1/2001

Abstract:
Self-compacting concrete (SCC) is highly workable concrete that can flow through congested structural elements under its own weight and adequately fill voids without segregation and excessive bleeding. Because of its complex mixture proportions, research on SCC has been highly empirical, and no models with reliable predictive capabilities for its behavior have been developed. Thus, its rheological and mechanical properties are often described using traditional regression analysis and statistical methods. The absence of a theoretical relationship between mixture proportioning and measured engineering properties is overcome by subjectively assuming certain empirical relationships based on limited experimental data, which are not applicable for conditions located outside the experimental domain, or when different materials are used. This paper demonstrates that artificial neural networks (ANN) can be used to predict the performance of SCC mixtures effectively. Inspired by the internal operation of the human brain, the ANN method has learning, self-organizing and auto-improving capabilities. Thus, it can capture complex interactions among input/output variables in a system without any prior knowledge of the nature of these interactions, and without having to explicitly assume a model form. Indeed, such a model form is generated by the data points themselves. This paper describes the database assembled, the architecture of the network selected, and the training process of the ANN model used. Initial tests show that the ANN method can accurately predict the slump flow, filling capacity, segregation, and compressive strength test results of SCC mixtures. A model for the acceptance/rejection of SCC mixtures based on knowledge of their mixture proportions is proposed and may be used after sufficient development of a more comprehensive database on an industrial scale for the proportioning of SCC with tailor-made properties.