Intelligent Design of Construction Materials: A Comparative Study of AI Approaches for Predicting the Strength of Concrete with Blast Furnace Slag

Abstract

Concrete production by replacing cement with green materials has been conducted in recent years considering the strategy of sustainable development. This study researched the topic of compressive strength regarding one type of green concrete containing blast furnace slag. Although some researchers have proposed using machine learning models to predict the compressive strength of concrete, few researchers have compared the prediction accuracy of different machine learning models on the compressive strength of concrete. Firstly, the hyperparameters of BP neural network (BPNN), support vector machine (SVM), decision tree (DT), random forest (RF), K-nearest neighbor algorithm (KNN), logistic regression (LR), and multiple linear regression (MLR) are tuned by the beetle antennae search algorithm (BAS). Then, the prediction effects of the above seven machine learning models on the compressive strength of concrete are evaluated and compared. The comparison results show that KNN has higher R values and lower RSME values both in the training set and test set; that is, KNN is the best model for predicting the compressive strength of concrete among the seven machine learning models mentioned above.

A Novel MBAS-RF Approach to Predict Mechanical Properties of Geopolymer-Based Compositions

“…The formula for R can be summarized as follows [ 84 , 85 , 86 , 87 , 88 , 89 ]: where and represent the average of predicted and actual values, respectively.…”

“…where n represents the number of datasets, i y * and i y represent the predicted and actual CS of geopolymer concrete, respectively. The formula for R can be summarized as follows [84][85][86][87][88][89]: where y * and y represent the average of predicted and actual values, respectively.…”

Understanding Penetration Attenuation of Permeable Concrete: A Hybrid Artificial Intelligence Technique Based on Particle Swarm Optimization

“…This research applied two parameters (RMSE, root-mean-square error; R, correlation coefficient) to validate the model and evaluate the prediction effect of the model established in this study. The RMSE was defined using the following formula [63,64]:…”

Preparation of Green Sustainable Cement Paste Mixture Based on Inorganic Additives: An Experimental and Modelling Approach

“…Influence of ceramic waste powder and PVA on geo-polymers [22] Experimental design, characterization and mechanical tests for different curing temperatures and at different ages Impact of curing temperature of alkaliactivated laterite-rock-powder-based geo-polymer samples [23] Experimental evaluation and characterization of cementbased composites by adding different materials Improvement of thermoelectric properties of large-sized thermoelectric cement composites for surface temperature reduction and pavement energy harvesting [24] Optimization of mechanical and durability properties and characterization of samples with different percentages of materials Enhancement in mechanical properties and durability of high-strength concrete with wheat straw ash as a partial replacement for cement [25] Characterization of the samples by using XRD, SEM, TEM, BET and MIP Study of mortars replaced with waste agriculture waste in the form of aerogel [26] Investigation of the predictive performance of various machine learning models for estimating compressive strength Determination of compressive strength of green concrete with blast furnace slag [27] Mechanical tests of the samples with different dosages of rice straw ash Evaluation of self-compacting concrete with rice straw ash as a partial replacement for cement at different time periods [28] Physical and mechanical testing of the samples containing different percentages of calcined sludge Study of cementitious materials with partial replacement of cement by sludge at different ages [29] A novel ultrasonic treatment using graphene quantum dots (GQDs) significantly improves the dispersion and exfoliation of 2D nanomaterials (GO, CLDH, CN), enhancing their ability to accelerate cement hydration and improve mechanical properties. This method increases the specific surface area and provides more nucleation sites, leading to better cement composite performance [30].…”