No abstract

Fly ash (FA) is a residual from thermal industries that has been effectively utilized in the production of FA-based geopolymer concrete (FGPC). To avoid time-consuming and costly experimental procedures, soft computing techniques, namely, random forest regression (RFR) and gene expression programming (GEP), are used in this study to develop an empirical model for the prediction of compressive strength of FGPC. A widespread, reliable, and consistent database of compressive strength of FGPC is set up via a comprehensive literature review. The database consists of 298 compressive strength data points. The influential parameters that are considered as input variables for modelling are curing temperature T , curing time t , age of the specimen A , the molarity of NaOH solution M , percent SiO2 solids to water ratio %   S / W in sodium silicate (Na2SiO3) solution, percent volume of total aggregate (   %   A G ), fine aggregate to the total aggregate ratio F / A G , sodium oxide (Na2O) to water ratio N / W in Na2SiO3 solution, alkali or activator to the FA ratio A L / F A , Na2SiO3 to NaOH ratio N s / N o , percent plasticizer ( %   P ), and extra water added as percent FA E W % . RFR is an ensemble algorithm and gives outburst performance as compared to GEP. However, GEP proposed an empirical expression that can be used to estimate the compressive strength of FGPC. The accuracy and performance of both models are evaluated via statistical error checks, and external validation is considered. The proposed GEP equation is used for sensitivity analysis and parametric study and then compared with nonlinear and linear regression expressions.

Supervised machine learning and its algorithm is an emerging trend for the prediction of mechanical properties of concrete. This study uses an ensemble random forest (RF) and gene expression programming (GEP) algorithm for the compressive strength prediction of high strength concrete. The parameters include cement content, coarse aggregate to fine aggregate ratio, water, and superplasticizer. Moreover, statistical analyses like MAE, RSE, and RRMSE are used to evaluate the performance of models. The RF ensemble model outbursts in performance as it uses a weak base learner decision tree and gives an adamant determination of coefficient R2 = 0.96 with fewer errors. The GEP algorithm depicts a good response in between actual values and prediction values with an empirical relation. An external statistical check is also applied on RF and GEP models to validate the variables with data points. Artificial neural networks (ANNs) and decision tree (DT) are also used on a given data sample and comparison is made with the aforementioned models. Permutation features using python are done on the variables to give an influential parameter. The machine learning algorithm reveals a strong correlation between targets and predicts with less statistical measures showing the accuracy of the entire model.