Comparison of Prediction Models Based on Machine Learning for the Compressive Strength Estimation of Recycled Aggregate Concrete

Evaluating the effectiveness of waste glass powder for the compressive strength improvement of cement mortar using experimental and machine learning methods

This study utilized both experimental testing and machine learning (ML) strategies to assess the effectiveness of waste glass powder (WGP) on the compressive strength (CS) of cement mortar. The cement-to-sand ratio was kept 1:1 with a water-to-cement ratio of 0.25. The superplasticizer content was 4% by cement mass, and the proportion of silica fume was 15%, 20%, and 25% by cement mass in three different mixes. WGP was added to cement mortar at replacement contents from 0 to 15% for sand and cement with a 2.5% increment. Initially, using an experimental method, the CS of WGP-based cement mortar at the age of 28 days was calculated. The obtained data were then used to forecast the CS using ML techniques. For CS estimation, two ML approaches, namely decision tree and AdaBoost, were applied. The ML model's performance was assessed by calculating the coefficient of determination (R²), performing statistical tests and k-fold validation, and assessing the variance between the experimental and model outcomes. The use of WGP enhanced the CS of cement mortar, as noted from the experimental results. Maximum CS was attained by substituting 10% WGP for cement and 15% WGP for sand. The findings of the modeling techniques demonstrated that the decision tree had a reasonable level of accuracy, while the AdaBoost predicted the CS of WGP-based cement mortar with a higher level of accuracy. Utilizing ML approaches will benefit the construction industry by providing efficient and economic approaches for assessing the properties of materials.

Bonding Mechanical Properties between SMA Fiber and ECC Matrix under Direct Pullout Loads

SMAF-ECC material composed of shape memory alloy fiber (SMAF) and engineered cementitious composite (ECC) has good bending and tensile properties, as well as good crack self-healing ability, energy consumption, and self-centering ability. The bond behavior between fiber and matrix is crucial to the effective utilization of the superelasticity of SMAF. The experimental study considered three variables: SMA fiber diameter, fiber end shape, and bond length. The pullout stress-strain curve of SMAF was obtained, and the maximum pullout stress, maximum bond stress, and fiber utilization rate were analyzed. Compared with the straight end and the hook end, the maximum pullout stress of the specimen using the knotted end SMAF is above 900 MPa, the fiber undergoes martensitic transformation, and the fiber utilization rate is above 80%, indicating that the setting of the knotted end can give full play to the superelasticity of the SMAF. Within the effective bond length range, increasing the bond length can increase the maximum anchorage force of the knotted end SMAF. Increasing the fiber diameter can increase the maximum pullout stress and maximum anchoring force of the knotted end SMAF but reduce the utilization rate of SMA fiber. This study provides a reliable theoretical basis for the bonding properties between SMAF and ECC.

Prediction of Stress-Strain Curves for HFRP Composite Confined Brick Aggregate Concrete under Axial Load

Recently, hemp-fiber-reinforced polymer (HFRP) composites have been developed to enhance the strength and ductility of normal and lightweight aggregate concrete along with recycled brick aggregate concrete. In addition, both experimental and analytical investigations have been performed to assess the suitability of the existing strength and strain models. However, the theoretical and analytical expressions to predict the stress-strain curves of HFRP-confined concrete were not developed. Therefore, the main objective of this study was to develop analytical expressions to predict the stress-strain curves of HFRP-confined waste brick aggregate concrete. For this purpose, a new experimental framework was conducted to examine the effectiveness of HFRP in improving the mechanical properties of concrete constructed with recycled brick aggregates. Depending on the strength of the concrete, two groups were formed, i.e., Type-1 concrete and Type-2 concrete. A total of sixteen samples were tested. The ultimate compressive strength and strain significantly increased due to HFRP confinement. Improvements of up to 272% and 457% in the ultimate compressive strength and strain were observed due to hemp confinement, respectively. To predict the ultimate compressive strength and strain of HFRP-confined concrete, this study investigated several existing analytical stress-strain models. Some of the strength models resulted in close agreement with experimental results, but none of the models could accurately predict the ultimate confined strain. Nonlinear regression analysis was conducted to propose expressions to predict the ultimate compressive strength and strain of HFRP-confined concrete. The proposed expressions resulted in good agreement with experimental results. An analytical procedure was proposed to predict the stress-strain curves of hemp-confined concrete constructed by partial replacement of natural coarse aggregates by recycled fired-clay brick aggregates. A close agreement was found between the experimental and analytically predicted stress-strain curves.

Study on Thermal Degradation Processes of Polyethylene Terephthalate Microplastics Using the Kinetics and Artificial Neural Networks Models

Because of its slow rate of disintegration, plastic debris has steadily risen over time and contributed to a host of environmental issues. Recycling the world’s increasing debris has taken on critical importance. Pyrolysis is one of the most practical techniques for recycling plastic because of its intrinsic qualities and environmental friendliness. For scale-up and reactor design, an understanding of the degradation process is essential. Using one model-free kinetic approach (Friedman) and two model-fitting kinetic methods (Arrhenius and Coats-Redfern), the thermal degradation of Polyethylene Terephthalate (PET) microplastics at heating rates of 10, 20, and 30 °C/min was examined in this work. Additionally, a powerful artificial neural network (ANN) model was created to forecast the heat deterioration of PET MPs. At various heating rates, the TG and DTG thermograms from the PET MPs degradation revealed the same patterns and trends. This showed that the heating rates do not impact the decomposition processes. The Friedman model showed activation energy values ranging from 3.31 to 8.79 kJ/mol. The average activation energy value was 1278.88 kJ/mol from the Arrhenius model, while, from the Coats-Redfern model, the average was 1.05 × 104 kJ/mol. The thermodynamics of the degradation process of the PET MPs by thermal treatment were all non-spontaneous and endergonic, and energy was absorbed for the degradation. It was discovered that an ANN, with a two-layer hidden architecture, was the most effective network for predicting the output variable (mass loss%) with a regression coefficient value of (0.951–1.0).

Experimental and machine learning approaches to investigate the effect of waste glass powder on the flexural strength of cement mortar

Using solid waste in building materials is an efficient approach to achieving sustainability goals. Also, the application of modern methods like artificial intelligence is gaining attention. In this regard, the flexural strength (FS) of cementitious composites (CCs) incorporating waste glass powder (WGP) was evaluated via both experimental and machine learning (ML) methods. WGP was utilized to partially substitute cement and fine aggregate separately at replacement levels of 0%, 2.5%, 5%, 7.5%, 10%, 12.5%, and 15%. At first, the FS of WGP-based CCs was determined experimentally. The generated data, which included six inputs, was then used to run ML techniques to forecast the FS. For FS estimation, two ML approaches were used, including a support vector machine and a bagging regressor. The effectiveness of ML models was assessed by the coefficient of determination (R2), k-fold techniques, statistical tests, and examining the variation amongst experimental and forecasted FS. The use of WGP improved the FS of CCs, as determined by the experimental results. The highest FS was obtained when 10% and 15% WGP was utilized as a cement and fine aggregate replacement, respectively. The modeling approaches' results revealed that the support vector machine method had a fair level of accuracy, but the bagging regressor method had a greater level of accuracy in estimating the FS. Using ML strategies will benefit the building industry by expediting cost-effective and rapid solutions for analyzing material characteristics.

Evaluating the compressive strength of glass powder-based cement mortar subjected to the acidic environment using testing and modeling approaches

This study conducted experimental and machine learning (ML) modeling approaches to investigate the impact of using recycled glass powder in cement mortar in an acidic environment. Mortar samples were prepared by partially replacing cement and sand with glass powder at various percentages (from 0% to 15%, in 2.5% increments), which were immersed in a 5% sulphuric acid solution. Compressive strength (CS) tests were conducted before and after the acid attack for each mix. To create ML-based prediction models, such as bagging regressor and random forest, for the CS prediction following the acid attack, the dataset produced through testing methods was utilized. The test results indicated that the CS loss of the cement mortar might be reduced by utilizing glass powder. For maximum resistance to acidic conditions, the optimum proportion of glass powder was noted to be 10% as cement, which restricted the CS loss to 5.54%, and 15% as a sand replacement, which restricted the CS loss to 4.48%, compared to the same mix poured in plain water. The built ML models also agreed well with the test findings and could be utilized to calculate the CS of cementitious composites incorporating glass powder after the acid attack. On the basis of the R2 value (random forest: 0.97 and bagging regressor: 0.96), the variance between tests and forecasted results, and errors assessment, it was found that the performance of both the bagging regressor and random forest models was similarly accurate.

Application of Soft-Computing Methods to Evaluate the Compressive Strength of Self-Compacting Concrete

This research examined machine learning (ML) techniques for predicting the compressive strength (CS) of self-compacting concrete (SCC). Multilayer perceptron (MLP), bagging regressor (BR), and support vector machine (SVM) were utilized for analysis. A total of 169 data points were retrieved from the various published articles. The data set was based on 11 input parameters, such as cement, limestone, fly ash, ground granulated blast-furnace slag, silica fume, rice husk ash, coarse aggregate, fine aggregate, superplasticizers, water, viscosity modifying admixtures, and one output with compressive strength of SCC. In terms of properly predicting the CS of SCC, the BR technique outperformed both the SVM and MLP models, as determined by the research results. In contrast to SVM and MLP, the coefficient of determination (R²) for the BR model was 0.95, whereas for SVM and MLP, the R² was 0.90 and 0.86, respectively. In addition, a k-fold cross-validation approach was adopted to check the accuracy of the employed models. The statistical measures mean absolute percent error, mean absolute error, and root mean square error ensure the validity of the model. Using sensitivity analysis, the influence of input factors on the intended CS of SCC was also explored. This analysis reveals that the highest contributing parameter towards the CS of SCC was cement with 16.2%, while rice husk ash contributed the least with 4.25% among all the input variables.

In-Depth Analysis of Cement-Based Material Incorporating Metakaolin Using Individual and Ensemble Machine Learning Approaches

In recent decades, a variety of organizational sectors have demanded and researched green structural materials. Concrete is the most extensively used manmade material. Given the adverse environmental effect of cement manufacturing, research has focused on minimizing environmental impact and cement-based product costs. Metakaolin (MK) as an additive or partial cement replacement is a key subject of concrete research. Developing predictive machine learning (ML) models is crucial as environmental challenges rise. Since cement-based materials have few ML approaches, it is important to develop strategies to enhance their mechanical properties. This article analyses ML techniques for forecasting MK concrete compressive strength (fc'). Three different individual and ensemble ML predictive models are presented in detail, namely decision tree (DT), multilayer perceptron neural network (MLPNN), and random forest (RF), along with the most effective factors, allowing for efficient investigation and prediction of the fc' of MK concrete. The authors used a database of MK concrete mechanical features for model generalization, a key aspect of any prediction or simulation effort. The database includes 551 data points with relevant model parameters for computing MK concrete's fc'. The database contains cement, metakaolin, coarse and fine aggregate, water, silica fume, superplasticizer, and age, which affect concrete's fc' but were seldom considered critical input characteristics in the past. Finally, the performance of the models is assessed to pick and deploy the best predicted model for MK concrete mechanical characteristics. K-fold cross validation was employed to avoid overfitting issues of the models. Additionally, ML approaches were utilized to combine SHapley Additive exPlanations (SHAP) data to better understand the MK mix design non-linear behaviour and how each input parameter's weighting influences the total contribution. Results depict that DT AdaBoost and modified bagging are the best ML algorithms for predicting MK concrete fc' with R² = 0.92. Moreover, according to SHAP analysis, age impacts MK concrete fc' the most, followed by coarse aggregate and superplasticizer. Silica fume affects MK concrete's fc' least. ML algorithms estimate MK concrete's mechanical characteristics to promote sustainability.

Evaluating the Strength and Impact of Raw Ingredients of Cement Mortar Incorporating Waste Glass Powder Using Machine Learning and SHapley Additive ExPlanations (SHAP) Methods

This research employed machine learning (ML) and SHapley Additive ExPlanations (SHAP) methods to assess the strength and impact of raw ingredients of cement mortar (CM) incorporated with waste glass powder (WGP). The data required for this study were generated using an experimental approach. Two ML methods were employed, i.e., gradient boosting and random forest, for compressive strength (CS) and flexural strength (FS) estimation. The performance of ML approaches was evaluated by comparing the coefficient of determination (R²), statistical checks, k-fold assessment, and analyzing the variation between experimental and estimated strength. The results of the ML-based modeling approaches revealed that the gradient boosting model had a good degree of precision, but the random forest model predicted the strength of the WGP-based CM with a greater degree of precision for CS and FS prediction. The SHAP analysis revealed that fine aggregate was a critical raw material, with a stronger negative link to the strength of the material, whereas WGP and cement had a greater positive effect on the strength of CM. Utilizing such approaches will benefit the building sector by supporting the progress of rapid and inexpensive approaches for identifying material attributes and the impact of raw ingredients.

Application of Ensemble Machine Learning Methods to Estimate the Compressive Strength of Fiber-Reinforced Nano-Silica Modified Concrete

In this study, compressive strength (CS) of fiber-reinforced nano-silica concrete (FRNSC) was anticipated using ensemble machine learning (ML) approaches. Four types of ensemble ML methods were employed, including gradient boosting, random forest, bagging regressor, and AdaBoost regressor, to achieve the study’s aims. The validity of employed models was tested and compared using the statistical tests, coefficient of determination (R²), and k-fold method. Moreover, a Shapley Additive Explanations (SHAP) analysis was used to observe the interaction and effect of input parameters on the CS of FRNSC. Six input features, including fiber volume, coarse aggregate to fine aggregate ratio, water to binder ratio, nano-silica, superplasticizer to binder ratio, and specimen age, were used for modeling. In predicting the CS of FRNSC, it was observed that gradient boosting was the model of lower accuracy and the AdaBoost regressor had the highest precision in forecasting the CS of FRNSC. However, the performance of random forest and the bagging regressor was also comparable to that of the AdaBoost regressor model. The R² for the gradient boosting, random forest, bagging regressor, and AdaBoost regressor models were 0.82, 0.91, 0.91, and 0.92, respectively. Also, the error values of the models further validated the exactness of the ML methods. The average error values for the gradient boosting, random forest, bagging regressor, and AdaBoost regressor models were 5.92, 4.38, 4.24, and 3.73 MPa, respectively. SHAP study discovered that the coarse aggregate to fine aggregate ratio shows a greater negative correlation with FRNSC’s CS. However, specimen age affects FRNSC CS positively. Nano-silica, fiber volume, and the ratio of superplasticizer to binder have both positive and deleterious effects on the CS of FRNSC. Employing these methods will promote the building sector by presenting fast and economical methods for calculating material properties and the impact of raw ingredients.

Predicting the Rheological Properties of Super-Plasticized Concrete Using Modeling Techniques

Interface yield stress (YS) and plastic viscosity (PV) have a significant impact on the pumpability of concrete mixes. This study is based on the application of predictive machine learning (PML) techniques to forecast the rheological properties of fresh concrete. The artificial neural network (NN) and random forest (R-F) PML approaches were introduced to anticipate the PV and YS of concrete. In comparison, the R-F model outperforms the NN model by giving the coefficient of determination (R2) values equal to 0.92 and 0.96 for PV and YS, respectively. In contrast, the model’s legitimacy was also verified by applying statistical checks and a k-fold cross validation approach. The mean absolute error, mean square error, and root mean square error values for R-F models by investigating the YS were noted as 30.36 Pa, 1141.76 Pa, and 33.79 Pa, respectively. Similarly, for the PV, these values were noted as 3.52 Pa·s, 16.48 Pa·s, and 4.06 Pa·s, respectively. However, by comparing these values with the NN’s model, they were found to be higher, which also gives confirmation of R-F’s high precision in terms of predicting the outcomes. A validation approach known as k-fold cross validation was also introduced to authenticate the precision of employed models. Moreover, the influence of the input parameters was also investigated with regard to predictions of PV and YS. The proposed study will be beneficial for the researchers and construction industries in terms of saving time, effort, and cost of a project.

Experimental Study and Theoretical Analysis on the Compression-Shear Multiaxial Mechanical Properties of Recycled Concrete

Recycled concrete, which is formed by replacing coarse aggregates in ordinary concrete with recycled aggregates (RA), is of great significance for the secondary utilization of waste building resources. In civil engineering, concrete structures are sometimes subjected to a compression–shear multiaxial stress state. Therefore, research on the compression–shear multiaxial mechanical properties of recycled concrete plays an important role in engineering practice. To explore the effect of RA replacement rate on the compression–shear properties of recycled concrete, an experimental study was carried out using a compression–shear testing machine and considering five RA replacement rates and five axial compression ratios. Consequently, the failure modes and mechanical property parameters under different working conditions were obtained and were used to analyze the effects of RA replacement rate and axial compression ratio on the shear stress of recycled concrete. Eventually, the following conclusions were reached: With the growth of axial compression ratio, the shear cracks exhibit a developing trend along the oblique direction, and the friction traces on the shear surface are gradually deepened. As the replacement rate increases, the number of shear cracks is gradually increased, accompanied by increasing broken fragments falling off from the shear interface. Since the action of the axial compression ratio can effectively improve the mechanical bite force and friction on the shear interface of recycled concrete, as the axial compression ratio increases, the shear stress is gradually increased. On the other hand, due to the initial damage of RA and its weak adhesion with cement mortar, the shear stress is gradually reduced with the increase of RA replacement rate. Meanwhile, the increase in shear stress shows a gradually decreasing trend with the growth of axial compression ratio. Specifically, for the RA replacement rates of 0% and 100%, the shear stress increased by 4.06 times and 3.21 times, respectively, under the influence of the axial compression ratio. Under different axial compression ratios, the shear stress was reduced by 43~46%, due to the increase of RA replacement rate. In addition, based on the octahedral stress space and the principal stress space, a compression–shear multiaxial failure criterion and shear stress calculation model for recycled concrete were proposed, by considering the effect of the RA replacement rate. The outcomes of this research are of great significance for engineering applications and the development of recycled concrete.

A Systematic Review of the Research Development on the Application of Machine Learning for Concrete

Research on the applications of new techniques such as machine learning is advancing rapidly. Machine learning methods are being employed to predict the characteristics of various kinds of concrete such as conventional concrete, recycled aggregate concrete, geopolymer concrete, fiber-reinforced concrete, etc. In this study, a scientometric-based review on machine learning applications for concrete was performed in order to evaluate the crucial characteristics of the literature. Typical review studies are limited in their capacity to link divergent portions of the literature systematically and precisely. Knowledge mapping, co-citation, and co-occurrence are among the most challenging aspects of innovative studies. The Scopus database was chosen for searching for and retrieving the data required to achieve the study’s aims. During the data analysis, the relevant sources of publications, relevant keywords, productive writers based on publications and citations, top articles based on citations received, and regions actively engaged in research into machine learning applications for concrete were identified. The citation, bibliographic, abstract, keyword, funding, and other data from 1367 relevant documents were retrieved and analyzed using the VOSviewer software tool. The application of machine learning in the construction sector will be advantageous in terms of economy, time-saving, and reduced requirement for effort. This study can aid researchers in building joint endeavors and exchanging innovative ideas and methods, due to the statistical and graphical portrayal of participating authors and countries.