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

Eco-Transformation of construction: Harnessing machine learning and SHAP for crumb rubber concrete sustainability

Researchers have focused their efforts on investigating the integration of crumb rubber as a substitute for conventional aggregates and cement in concrete. Nevertheless, the manufacture of crumb rubber concrete (CRC) has been linked to the release of noxious pollutants, hence presenting potential environmental hazards. Rather than developing novel CRC formulations, the primary objective of this work is to construct an extensive database by leveraging prior research efforts. The study places particular emphasis on two crucial concrete properties: compressive strength (fc') and tensile strength (fts). The database includes a total of 456 data points for fc' and 358 data points for fts, focusing on nine essential characteristics that have a substantial impact on both attributes. The research employs several machine learning algorithms, including both individual and ensemble methods, to undertake a comprehensive analysis of the created databases for fc' and fts. In order to ascertain the correctness of the models, a comparative analysis of machine learning techniques, namely decision tree (DT) and random forest (RF), is conducted using statistical evaluation. Cross-validation approaches are used in order to address the possible issues of overfitting. Furthermore, the Shapley additive explanations (SHAP) approach is used to investigate the influence of input parameters and their interrelationships. The findings demonstrate that the RF methodology has superior performance compared to other ensemble techniques, as shown by its lower error rates and higher coefficient of determination (R2) of 0.87 and 0.85 for fc' and fts respectively. When comparing ensemble approaches, it can be seen that AdaBoost outperforms bagging by 6 % for both outcome models and individual decision tree learners by 17% and 21% for fc' and fts respectively in terms of performance. The average accuracy of AdaBoost algorithm for both the models is 84%. Significantly, the age and the inclusion of crumb rubber in CRC are identified as the primary criteria that have a substantial influence on the mechanical properties of this particular kind of concrete.

Splitting tensile strength prediction of Metakaolin concrete using machine learning techniques

Splitting tensile strength (STS) is an important mechanical property of concrete. Modeling and predicting the STS of concrete containing Metakaolin is an important method for analyzing the mechanical properties. In this paper, four machine learning models, namely, Artificial Neural Network (ANN), support vector regression (SVR), random forest (RF), and Gradient Boosting Decision Tree (GBDT) were employed to predict the STS. The comprehensive comparison of predictive performance was conducted using evaluation metrics. The results indicate that, compared to other models, the GBDT model exhibits the best test performance with an R2 of 0.967, surpassing the values for ANN at 0.949, SVR at 0.963, and RF at 0.947. The other four error metrics are also the smallest among the models, with MSE = 0.041, RMSE = 0.204, MAE = 0.146, and MAPE = 4.856%. This model can serve as a prediction tool for STS in concrete containing Metakaolin, assisting or partially replacing laboratory compression tests, thereby saving costs and time. Moreover, the feature importance of input variables was investigated.

Estimation of concrete materials uniaxial compressive strength using soft computing techniques

This study addresses a critical gap in concrete strength prediction by conducting a comparative analysis of three deep learning algorithms: convolutional neural networks (CNNs), gated recurrent units (GRUs), and long short-term memory (LSTM) networks. Unlike previous studies that employed various machine learning algorithms on diverse concrete types, our study focuses on mixed-design concrete and fine-tuned deep learning algorithms. The objective is to identify the optimal deep learning (DL) algorithm for predicting concrete uniaxial compressive strength, a crucial parameter in construction and structural engineering. The dataset comprises experimental records for mixed-design concrete, and models were developed and optimized for predictive accuracy. The results show that the CNN model consistently outperformed GRU and LSTM. Hyperparameter tuning and regularization techniques further improved model performance. This research offers practical solutions for material property prediction in the construction industry, potentially reducing resource burdens and enhancing efficiency and construction quality.

Corrosion Activity of Stainless Steel SS430 and Carbon Steel B450C in a Sodium Silicate Modified Limestone-Portland Cement Extract

Stainless steel SS430 and carbon steel B450C were exposed for 30 days to the aqueous extract of sodium silicate-modified limestone-Portland cement as an alternative for the partial replacement of the Portland cement clinker. The initial pH of 12.60 was lowered and maintained at an average of 9.60, associated with air CO₂ dissolution and acidification. As a result, the carbon steel lost its passive state, and the corrosion potential (OCP) reached a negative value of up to 296 mV, forming the corrosion layer of FeO, and FeOOH. In the meaning time, on the stainless steel SS430 surface, a passive layer of Cr₂O₃ grew in the presence of FeO, Fe₂O₃ and Cr(OH)₃ corrosion products; thus, the OCP shifted to more positive values of +150 mV. It is suggested that a self-repassivation process took place on the SS430 surface due to the accumulation of alkaline sulfates on the interface. Because of the chloride attack, SS430 presented isolated pits, while on B450C, their area was extended. The quantitative analysis of EIS Nyquist and Bode diagrams revealed that the Rp of the corrosion process for SS430 was 2500 kΩcm², ≈32 times lower in magnitude than on B450C, for which the passive layer tended to disappear, while that on SS430 was ≈0.82 nm.

A Machine-Learning-Based Approach for Predicting Mechanical Performance of Semi-Porous Hip Stems

Novel designs of porous and semi-porous hip stems attempt to alleviate complications such as aseptic loosening, stress shielding, and eventual implant failure. Various designs of hip stems are modeled to simulate biomechanical performance using finite element analysis; however, these models are computationally expensive. Therefore, the machine learning approach is incorporated with simulated data to predict the new biomechanical performance of new designs of hip stems. Six types of algorithms based on machine learning were employed to validate the simulated results of finite element analysis. Afterwards, new designs of semi-porous stems with outer dense layers of 2.5 and 3 mm and porosities of 10-80% were used to predict the stiffness of the stems, stresses in outer dense layers, stresses in porous sections, and factor of safety under physiological loads using machine learning algorithms. It was determined that decision tree regression is the top-performing machine learning algorithm as per the used simulation data in terms of the validation mean absolute percentage error which equals 19.62%. It was also found that ridge regression produces the most consistent test set trend as compared with the original simulated finite element analysis results despite relying on a relatively small data set. These predicted results employing trained algorithms provided the understanding that changing the design parameters of semi-porous stems affects the biomechanical performance without carrying out finite element analysis.

Ensemble Machine-Learning-Based Prediction Models for the Compressive Strength of Recycled Powder Mortar

Recycled powder (RP) serves as a potential and prospective substitute for cementitious materials in concrete. The compressive strength of RP mortar is a pivotal factor affecting the mechanical properties of RP concrete. The application of machine learning (ML) approaches in the engineering problems, particularly for predicting the mechanical properties of construction materials, leads to high prediction accuracy and low experimental costs. In this study, 204 groups of RP mortar compression experimental data are collected from the literature to establish a dataset for ML, including 163 groups in the training set and 41 groups in the test set. Four ensemble ML models, namely eXtreme Gradient-Boosting (XGBoost), Random Forest (RF), Light Gradient-Boosting Machine (LightGBM) and Adaptive Boosting (AdaBoost), were selected to predict the compressive strength of RP mortar. The comparative results demonstrate that XGBoost has the highest prediction accuracy when the a10-index, MAE, RMSE and R² of the training set are 0.926, 1.596, 2.155 and 0.950 and the a10-index, MAE, RMSE and R² of the test set are 0.659, 3.182, 4.285 and 0.842, respectively. SHapley Additive exPlanation (SHAP) is adopted to interpret the prediction process of XGBoost and explain the influence of influencing factors on the compressive strength of RP mortar. According to the importance of influencing factors, the order is the mass replacement rate of RP, the size of RP, the kind of RP and the water binder ratio of RP. The compressive strength of RP mortar decreases with the increase in the RP mass replacement rate. The compressive strength of RBP mortar is slightly higher than that of RCP mortar. Machine learning technologies will benefit the construction industry by facilitating the rapid and cost-effective evaluation of RP material properties.

Corrosion Activity of Carbon Steel B450C and Stainless Steel SS430 Exposed to Extract Solution of a Supersulfated Cement

Carbon steel B450C and low-chromium stainless steel SS430 were exposed for 30 days to supersulfated "SS1" cement extract solution, considered as a "green" alternative for partial replacement of the Portland cement clinker. The initial pH of 12.38 dropped since the first day to 7.84, accompanied by a displacement to more negative values of the free corrosion potential (OCP) of the carbon steel up to ≈-480.74 mV, giving the formation of γ-FeOOH, α-FeOOH and Fe2O3, as suggested by XRD and XPS analysis. In the meantime, the OCP of the SS430 tended towards more positive values (+182.50 mV), although at lower pH, and XPS analysis revealed the presence of Cr(OH)3 and FeO as corrosion products, as well the crystals of CaCO3, NaCl and KCl. On both surfaces, a localized corrosion attack was observed in the vicinity of local cathodes (Cu, Mn-carbides, Cr-nitrides, among others), influenced by the presence of Cl- ions in the "SS1" extract solution, originating from the pumice. Two equivalent circuits were proposed for the quantitative analysis of EIS Nyquist and Bode diagrams, whose data were correlated with the OCP values and pH change in time of the "SS1" extract solution. The thickness of the corrosion layer formed on the SS430 surface was ≈0.8 nm, while that on the B450C layer was ≈0.3 nm.