A tremendous volumetric increase in waste marble powder as industrial waste has recently resulted in high environmental concerns of water, soil and air pollution. In this paper, we exploit the capabilities of machine learning to compressive strength prediction of concrete incorporating waste marble powder for future use. Experimentation has been carried out using different compositions of waste marble powder in concrete and varying water binder ratios of 0.35, 0.40 and 0.45 for the analysis. Effect of different dosages of superplasticizer has also been considered. In this paper, different regression algorithms to analyse the effect of waste marble powder on concrete, viz., multiple linear regression, K-nearest neighbour, support vector regression, decision tree, random forest, extra trees and gradient boosting, have been exploited and their efficacies have been compared using various statistical metrics. Experiments reveal random forest as the best model for compressive strength prediction with an R2 value of 0.926 and mean absolute error of 1.608. Further, shapley additive explanations and variance inflation factor analysis showcase the capabilities of the best achieved regression model in optimizing the use of marble powder as partial replacement of cement in concrete.

Concrete is one of the most important and versatile construction materials and variation in its properties is inevitable. Mix design of concrete is done in such a way that the design compressive strength is typically higher than the actual values specified by the structural engineer. The concept of reliability has not been explicitly used in regard of calculation of compressive strength using mix design and demands attention. A design procedure based on the reliability‐based index is presented. The design procedure is developed for the concrete mix with partial replacement of cement by marble dust. The mechanical property which is the compressive strength of the concrete mix design is considered as a random variable, assumed to be lognormally distributed. The present study makes an effort to design a concrete mix in accordance to theory of confidence level for various levels of reliability. Mix design guidelines and graphs for various levels of replacement of cement by marble dust have also been presented in the study. Also, the cost analysis of various design mix proportions used has been calculated and compared. Four different cases to illustrate the performance rating in accordance with replacement levels of Marble dust have been formulated. The concrete mixes with marble dust induced in concrete had lower partial safety factors than those without inclusion. The characteristics of Marble dust incorporated concrete have been assigned numerical performance index values. These values may constitute a reliable means for concrete producers in finding the rate of cement replacement by other cementitious materials. The compressive strength of most of mixes with marble dust had a coefficient of variation and within‐test coefficient of variation value ranging between 2% and 3% and less than 1.5%, respectively. This indicates toward improvement in quality of concrete with cement partially replaced by marble dust.

No abstract