Search

Purpose: 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. Design/methodology/approach: 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. Findings: 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. Originality/value: 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. [ABSTRACT FROM AUTHOR]

This paper reported on the micro-level properties of alkali-activated pastes cured in ambient conditions. The mechanisms influencing setting time and the microstructure development of fly ash, slag, and metakaolin were studied. The mortar compressive strength of the binders and their ultrasonic pulse velocity (UPV) were tested after 56 days of ambient curing. The micro-level properties of paste cured at ambient conditions for seven days were determined to understand the phases developed. NASH gel was observed to delay setting and possessed lower compressive strength, while CASH gel was set early and possessed high compressive strength. The micro-characterisation of the alkali-activated binder system developed with fly ash and metakaolin showed the presence of NASH gel. The alkali-activated binder system developed with GGBS contained multiple gels, such as N, C-ASH, and CSH. The molecular structures of CSH, CASH, NASH, and N, C-ASH are also presented and were obtained using high score plus software. [ABSTRACT FROM AUTHOR]