Modelization of the rheological behavior of self-compacting concrete using artificial neural networks

• Published in: Materials today : proceedings Vol. 58; pp. 1114 - 1121
• Main Authors: El Asri, Yousef, Ben Aicha, Mouhcine, Zaher, Mounir, Hafidi Alaoui, Adil
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 2022
• Subjects: Artificial neural networks; Empirical tests; Rheological parameters; Self-compacting concrete; Self-compacting concrete; Rheological parameters; Empirical tests; Artificial neural networks
• ISSN: 2214-7853; 2214-7853
• DOI: 10.1016/j.matpr.2022.01.257

Self-Compacting Concrete (SCC) is a fluid concrete designed to flow freely through obstacles (reinforcement) in order to completely fill the formwork without segregation or bleeding. The appearance of this class of concrete increases the need to precisely characterize their behavior during flow. At present, there are several empirical tests to characterize a SCC such as slump flow, L-box and V-Funnel, but no correlation, based on artificial intelligence, has been proposed for the determination of the rheological behavior (plastic viscosity and the yield stress) as a function of rheological parameters found during empirical tests (slump flow diameter, H2/H1 ratio of L-Box and V-Funnel flow time). The objective of this study, numerical and experimental, is to search an optimum correlation between behavior and rheological parameters using the techniques of artificial intelligence, and more precisely, artificial neural networks.