Revealing the nature of metakaolin-based concrete materials using artificial intelligence techniques

Architecture of the optimum BPNN 6-21-1 Artificial Neural Network. [Display omitted] •The sensitivity of metakaolin-based concrete materials compressive strength on mix parameters has been investigated and measured.•Artificial Neural Network modelss, namely for the prediction of the compressive strength of concrete have been developed.•Performance prediction of the predictive models was assessed and compared. In this study, a model for the estimation of the compressive strength of concretes incorporating metakaolin is developed and parametrically evaluated, using soft computing techniques. Metakaolin is a component extensively employed in recent decades as a means to reduce the requirement for cement in concrete. For the proposed models, six parameters are accounted for as input data. These are the age at testing, the metakaolin percentage in relation to the total binder, the water-to-binder ratio, the percentage of superplasticizer, the binder to sand ratio and the coarse to fine aggregate ratio. For training and verification of the developed models a database of 867 experimental specimens has been compiled, following a broad survey of the relevant published literature. A robust evaluation process has been utilized for the selection of the optimum model, which manages to estimate the concrete compressive strength, accounting for metakaolin usage, with remarkable accuracy. Using the developed model, a number of diagrams is produced that reveal the highly non-linear influence of mix components to the resulting concrete compressive strength.