A comprehensive GEP and MEP analysis of a cement-based concrete containing metakaolin

Abstract

Due to the detrimental environmental consequence of cement formation, studies has concentrated on decreasing the environmental influence and expense of cement containing products. It is crucial to conduct research on the mechanical characteristics of cement additive/replacement products such as metakaolin (MK). To serve the said purpose, the importance of developing predictive machine learning (ML) models is growing as ecological concerns intensify. Since there are few ML approaches for them, it is imperative to develop techniques to improve the mechanical properties of such products. In order to overcome these issues, this research examines ML methods for forecasting the compressive strength (fc') of concrete containing MK. Gene expression programming (GEP) and multigene expression programming (MEP), two distinct ML predictive models, are provided in detail along with the most useful variables, enabling effective analysis and forecasting of the fc' of concrete containing MK. An important component of any prediction or simulation endeavor is model generalization, and the researchers of this study used a data set of MK concrete mechanical properties for this purpose. The database has 405 data points with pertinent model parameters to calculate the fc' of concrete containing MK. Cement, percentage of metakaolin by binder, coarse and fine aggregate by binder, water by binder, coarse aggregates by fine aggregates, percentage of superplasticizer by binder, and age are among the factors in the database that influence concrete's fc' yet still previously infrequently regarded as crucial input attributes. The effectiveness of the models is then examined in order to choose and implement the best predicted model for the mechanical properties of MK-based concrete. According to the findings of this research, the optimal ML algorithms for forecasting MK-based concrete fc' is MEP with R2 value of 0.96. Additionally, the sensitivity analysis shows that water-by-binder, percentage of superplasticizer-by-binder and age have the significant effect on the development of compressive strength of metakaolin based concrete. GEP and MEP models develop empirical expression for the outcome to forecast future databases' features to promote the usage of sustainable MK concrete. Moreover, detrimental effects caused by intensive and costly labor work can be overcome by utilizing these environmental-friendly techniques.