Adaptive Fuzzy Logic Models for the Prediction of Compressive Strength of Sustainable Concrete

Abstract

Sustainable growth has encouraged the utilisation of waste materials in conventional concrete for replacement. This study focuses on concrete produced by partially replacing cement and sand with waste products, like slag and fly ash. The application of these materials in concrete lowers the global energy demand and also saves money on the verge of depletion. These materials provide increased mechanical and durability properties as well as a wide range of advantages, including decreased strain on natural resources, and a lower carbon footprint. Experimental work pertaining to concrete contributes to the waste of resources, time and money. Over the last four decades, the development of methods for seeking optimal mixing proportions has been the focus of research. Several researchers have worked in recent years to establish reliable concrete models of compressive force prediction. The prediction of compressive strength of concrete is therefore an active research area. An alternative approach that used machine learning has recently gained momentum in the field of civil engineering. Machine learning is a soft computing mechanism that embodies the characteristics of the human brain, learns from prior circumstances and adapts without any restrictions to new environments. In this research work, a model has been proposed to predict the compressive strength of concrete comprising slag and fly ash as partial substitutes. The first section encompasses a brief summary of the works done by different researchers in this field, and the factors affecting the compressive strength of concrete. The next segment elaborates upon fuzzy logic and the proposed model used to predict the compressive strength of different design mixes. Thereafter the results are compared and evaluated. The objective of this study is to develop a model that can be deployed to predict the compressive strength of different types of concrete mixes.