Prediction of compressive strength of geopolymer concrete using machine learning techniques

Nowadays, the accurate prediction of strength properties of cementitious materials containing nano‐ and micro‐silica (NS–MS) remains an open question because of the highly nonlinear function of its constituents on the porosity. In the present study, a combined framework is developed by integrating ant colony optimization (ACO), particle swarm optimization (PSO), and biogeography‐based optimization (BBO) with the artificial neural network (ANN) to predict compressive and flexural strengths of cement mortar in two different forms of ignoring (ANNII) and considering (ANNIII) the porosity as an input parameter. This procedure is accomplished considering the porosity effect on the strengths and implementing an experimental program containing 32 mixes (960 specimens) with different NS–MS contents at various ages. Macro‐ and micro‐structural analyses showed that NS–MS caused more decreased pore structure, and thus this situation increases strength properties compared to their separate use. Also, MBBO‐MOANNIII results indicated an improvement in convergence speed and model accuracy compared to other models. This improvement is because of considering the porosity.

Section: Introductionmentioning

confidence: 99%

New insight into the prediction of strength properties of cementitious mortar containing nano‐ and micro‐silica based on porosity using hybrid artificial intelligence techniques

Kazemi

Eskandari‐Naddaf

Korouzhdeh

2023

“…63 When used to predict the compressive strength of geopolymer concrete, the ensemble ML techniques boosting and AdaBoost (AdB) demonstrated a high value of R 2 equal to 0.960 and 0.930, respectively. 64 Recently, Gupta et al 65 developed ANN model containing two hidden layers for predicting the compressive strength of geopolymer, the ANN model can be achieved with high performance R 2 = 0.904 for testing datasets. Different investigations of ML model application for predicting compressive strength of geopolymer concrete is summarized in Table 1.…”

Section: Introductionmentioning

confidence: 99%

Data‐driven approach for investigating and predicting of compressive strength of fly ash–slag geopolymer concrete

Tran

2023

Fly ash–slag geopolymer concrete is an intangible material that does not use conventional Portland cement, thereby reducing CO2 emissions into the environment, and helping to increase sustainable development. However, compared with conventional concrete, the compressive strength of fly ash–slag geopolymer concrete is complexly dependent on many factors. Using the data‐driven approach for investigating and predicting fly ash–slag geopolymer concrete compressive strength is a suitable choice. This study introduces 11 easily accessible machine learning models in open‐source libraries of the Python programming language such as support vector machine, random forest (RF), gradient boosting (GB), AdaBoost, decision trees, light GB machine, extreme GB (XGB), K‐nearest neighbors, multivariable regression, Gaussian process regression, and CatBoost (CatB). Based on a dataset of 158 samples, 14 inputs, and 1 output variable compressive strength, the performance of 11 machine learning models was evaluated through 4 criteria including coefficient of determination, root mean square error, mean absolute error, and mean absolute percentage error combined with 10 repeats of 10‐fold cross‐validation. Four models have the best performance based on the above four criteria value in determining compressive strength for testing dataset sorted descending is CatB > XGB > RF > GB. Global Shapley (SHAP) value‐based CatB and XGB indicates three groups of factors with decreasing influence on compressive strength of geopolymer concrete: group I (slag, molarity, coarse aggregate, curing temperature, and alkaline activator/binder) > group II (Na2SiO3 content, NaOH content, fine aggregate, fly ash content), curing period > group III (extra water added, NaOH/Na2SiO3, superplasticizer content, rest period). Extra water added, NaOH/Na2SiO3, superplasticizer content, rest period have insignificant influence on the compressive strength value of geopolymer concrete. The greater the slag content in the slag–fly ash mixture, the greater the compressive strength of geopolymer concrete. The optimum molarity of NaOH concentration is about 14–16 M for designing the compressive strength of geopolymer concrete. SHAP values partial dependence plots (PDP) and PDP indicate that alkaline activator/binder optimal values exist to achieve high compressive strength. The compressive strength increases with curing temperature between 20 and 100°C. PDP values show that the tendency to increase compressive strength with increasing coarse aggregate content from about 750 to 1250 kg/m3.

“…The three‐layer Bayesian‐regularized ANN model with 10 neurons in every layer, according to the study, is the best model for estimating Geo‐p concrete CS ( R = 0.99 and MSE = 1.017). Gupta and Rao 30 used multivariate nonlinear regression, multiple linear regression, and ANN to estimate the CS of Geo‐p concrete 31 . Khan et al 31 used ANN, ANFIS, multi‐gene expression programming (MEP) to estimate the CS and thermal conductivity of hemp‐based bio‐composites.…”

Section: Introductionmentioning

confidence: 99%

Prognosis of compressive strength of fly‐ash‐based geopolymer‐modified sustainable concrete with ML algorithms

Kumar

Arora

Kapoor

et al. 2022

Sustainable concrete is the demand of the present era to reduce carbon emissions. Fly‐ash‐based geopolymer (FLAG) concrete has been used in the construction industry for more than one and a half decades. The compressive strength (CS) of concrete plays a crucial role in the mechanical properties of concrete. Laboratory experiments take a huge amount of time and cost to estimate the CS of concrete. Although analytical methods exist to estimate the CS of concrete, but these models cannot forecast the CS of concrete with better precision due to the complexity of the design mixes. The machine learning (ML)‐based models have been helpful in estimating the CS of concrete with high accuracy and reliability. In this article, four ML algorithms (support vector machine [SVM], linear regression [LR], ensemble learning [EL], and Gaussian process regression [GPR]) and three optimized ML algorithms (EL, SVM, and GPR) have been used to estimate the CS of FLAG concrete. The R‐value of LR, EL, SVMR, GPR, optimized EL, optimized SVMR and optimized GPR models are 0.8916, 0.9172, 0.9313, 0.9529, 0.9459, 0.9348 and 0.9590, respectively. The accuracy of the optimized GPR model with an R‐value of 0.9590 and RMSE value of 1.7132 MPa outperformed all other ML models. The performances of all the developed models have been illustrated through Taylor diagram and error plot. The feature importance of the input parameters has been explained with the explainable ML technique. The developed, optimized GPR model can be reliable tool to estimate the CS with greater accuracy and also reducing time and cost.