Application of Soft Computing Techniques to Predict the Strength of Geopolymer Composites

Qichen Wang,Ayaz Ahmad,Fahid Aslam,Abdullah Mohamed,Waqas Ahmad,Nikolai Ivanovich Vatin

doi:10.3390/polym14061074

Abstract

Geopolymers may be the best alternative to ordinary Portland cement because they are manufactured using waste materials enriched in aluminosilicate. Research on geopolymer composites is accelerating. However, considerable work, expense, and time are needed to cast, cure, and test specimens. The application of computational methods to the stated objective is critical for speedy and cost-effective research. In this study, supervised machine learning approaches were employed to predict the compressive strength of geopolymer composites. One individual machine learning approach, decision tree, and two ensembled machine learning approaches, AdaBoost and random forest, were used. The coefficient correlation (R2), statistical tests, and k-fold analysis were used to determine the validity and comparison of all models. It was discovered that ensembled machine learning techniques outperformed individual machine learning techniques in forecasting the compressive strength of geopolymer composites. However, the outcomes of the individual machine learning model were also within the acceptable limit. R2 values of 0.90, 0.90, and 0.83 were obtained for AdaBoost, random forest, and decision models, respectively. The models’ decreased error values, such as mean absolute error, mean absolute percentage error, and root-mean-square errors, further confirmed the ensembled machine learning techniques’ increased precision. Machine learning approaches will aid the building industry by providing quick and cost-effective methods for evaluating material properties.

Highlights

Introduction iationsCement-based conventional concrete (CBCC) is the most broadly utilized type of construction material on a global scale [1–3]
This study aims to identify the most suitable machine learning (ML) technique for the compressive strength (CS) of GPCs in terms of results prediction and the influence of input parameters on the model’s performance
The percentage distribution of error values was it was discovered that 37.4% of values were less than 3 MPa, 38.5% were between 3 and determined, and it was discovered that 37.4% of values were less than 3 MPa, 38.5% were

Summary

Introduction

Cement-based conventional concrete (CBCC) is the most broadly utilized type of construction material on a global scale [1–3]. The primary constituents of CBCC are aggregates, water, and ordinary Portland cement (OPC) [4,5]. The manufacture of OPC produces large quantities of greenhouse gases, i.e., CO2 , which substantially add to climate change [8–10]. The production of OPC is anticipated to release 1.35 billion tons of greenhouse emissions annually [11–13]. Scholars have focused their attempts on minimizing OPC usage through the use of alternate binder types. Alternatives to CBCC may include alkaliactivated compounds such as geopolymers [14–16]. When precursors and activators react, alkali-activated compounds are formed. They have been categorized into two kinds based

Objectives

Methods

Results

Conclusion