Proposing a Model for Compressive Strength Prediction of Self Compacting Concrete Using ANN

Document Type : Original Article

Authors

1 M.Sc. Student, Department of Civil Engineering, Faculty of Engineering, Lorestan University, Khorramabad, Iran

2 Professor, Department of Civil Engineering, Faculty of Engineering, Lorestan University, Khorramabad, Iran

3 Ph.D. Student, Science and Research Branch, Islamic Azad University, Tehran, Iran

10.22091/cer.2024.11015.1564

Abstract

Self-compacting concrete (SCC) is a dynamic field in construction worldwide. This type of concrete encompasses a wide range of mix designs that possess the necessary fresh and hardened concrete properties for specific applications. Although strength remains the primary criterion for the success of SCC, its fresh concrete properties are significantly broader than those of conventional vibrated concrete. These desirable properties must be maintained during placement and at the site. SCC is a preferred option in cases where reinforcement bars are densely arranged. Moreover, the absence of the need for vibrators significantly reduces environmental noise pollution. Despite its favorable features, the mix design and execution of SCC depend on various factors, such as the gradation of aggregates, the type of additives, and the fillers used. Considering each of these criteria influences the quality of hardened concrete and the workability of fresh concrete. This research has been conducted due to the need for improving accuracy and efficiency in SCC mix design and reducing the time and cost of physical testing. In this paper, the strength of SCC has been predicted using laboratory data and the application of artificial neural networks. The results indicate a high level of accuracy in the estimates made through soft computing techniques.

Keywords

Main Subjects

Send comment about this article
CAPTCHA Image
Civil Infrastructure Researches

Articles in Press, Accepted Manuscript
Available Online from 20 October 2024

Files

Share

How to cite

Statistics