Search results

This study aims to present the results of an experimental evaluation of low (M30), mid (M40) and high (M50) grade self-compacting concrete (SCC) with three nominal maximum aggregate sizes (NMAS), namely, 20 mm, 16 mm and 12.5 mm, with Bailey gradation (BG) in comparison with Indian standard gradation (ISG).

This study was conducted in a laboratory by testing the characteristics of fresh and hardened properties of self-compacting concrete.

Rheological and mechanical properties of SCC were evaluated in detail and according to the results, a concrete sample containing lower NMAS with BG demonstrated improvement in modulus of elasticity and compressive strength, while improving the rheological properties as well. Meanwhile, SCC demonstrated poor performance in split tensile and flexural strengths with lower NMAS gradations and a direct correlation was evident as the increase in NMAS caused an increase in the strength and vice-versa.

Upon comparison of BG with ISG, it was revealed that BG mixes succeeded to demonstrate superior performance. From the material optimization, rheological and mechanical performance study, it is recommended that BG with NMAS 16 mm can be used for conventional SCC.

The compressive strength of concrete depends on many interdependent parameters; its exact prediction is not that simple because of complex processes involved in strength development. This study aims to predict the compressive strength of normal concrete and high-performance concrete using four datasets.

In this paper, five established individual Machine Learning (ML) regression models have been compared: Decision Regression Tree, Random Forest Regression, Lasso Regression, Ridge Regression and Multiple-Linear regression. Four datasets were studied, two of which are previous research datasets, and two datasets are from the sophisticated lab using five established individual ML regression models.

The five statistical indicators like coefficient of determination (R²), mean absolute error, root mean squared error, Nash–Sutcliffe efficiency and mean absolute percentage error have been used to compare the performance of the models. The models are further compared using statistical indicators with previous studies. Lastly, to understand the variable effect of the predictor, the sensitivity and parametric analysis were carried out to find the performance of the variable.

The findings of this paper will allow readers to understand the factors involved in identifying the machine learning models and concrete datasets. In so doing, we hope that this research advances the toolset needed to predict compressive strength.