Accurate prediction of concrete compressive strength can minimize the need for extensive, time-consuming, and costly mixture optimization testing and analysis. This study attempts to enhance the prediction accuracy of compressive strength using stacking ensemble machine learning (ML) with feature engineering techniques. Seven alternative ML models of increasing complexity were implemented and compared, including linear regression, SVM, decision tree, multiple layer perceptron, random forest, Xgboost and Adaboost. To further improve the prediction accuracy, a ML pipeline was proposed in which the feature engineering technique was implemented, and a two-layer stacked model was developed. The k-fold cross-validation approach was employed to optimize model parameters and train the stacked model. The stacked model showed superior performance in predicting concrete compressive strength with a correlation of determination (R²) of 0.985. Feature (i.e., variable) importance was determined to demonstrate how useful the synthetic features are in prediction and provide better interpretability of the data and the model. The methodology in this study promotes a more thorough assessment of alternative ML algorithms and rather than focusing on any single ML model type for concrete compressive strength prediction.

Due to the non-uniform distribution of meso-structure, the diffusion of chloride ions in concrete show the characteristics of characteristics of randomness and fuzziness, which leads to the non-uniform distribution of chloride ions and the non-uniform corrosion of steel rebar in concrete. This phenomenon is supposed as the main reason causing the uncertainty of the bearing capacity deterioration of reinforced concrete structures. In order to analyze and predict the durability of reinforced concrete structures under chloride environment, the random features of chloride ions transport in concrete were studied in this research from in situ meso-structure of concrete. Based on X-ray CT technology, the spatial distribution of coarse aggregates and pores were recognized and extracted from a cylinder concrete specimen. In considering the influence of ITZ, the in situ mesostructure of concrete specimen was reconstructed to conduct a numerical simulation on the diffusion of chloride ions in concrete, which was verified through electronic microprobe technology. Then a stochastic study was performed to investigate the distribution of chloride ions concentration in space and time. The research indicates that the influence of coarse aggregate on chloride ions diffusion is the synthetic action of tortuosity and ITZ effect. The spatial distribution of coarse aggregates and pores is the main reason leading to the non-uniform distribution of chloride ions both in spatial and time scale. The chloride ions concentration under a certain time and the time under a certain concentration both satisfy the Lognormal distribution, which are accepted by Kolmogorov-Smirnov test and Chi-square test. This research provides an efficient method for obtain mass stochastic data from limited but representative samples, which lays a solid foundation for the investigation on the service properties of reinforced concrete structures.

Experimenting with concrete to determine its compressive and tensile strengths is a laborious and time-consuming operation that requires a lot of attention to detail. Researchers from all around the world have spent the better part of the last several decades attempting to use machine learning algorithms to make accurate predictions about the technical qualities of various kinds of concrete. The research that is currently available on estimating the strength of concrete draws attention to the applicability and precision of the various machine learning techniques. This article provides a summary of the research that has previously been conducted on estimating the strength of concrete by making use of a variety of different machine learning methods. In this work, a classification of the existing body of research literature is presented, with the classification being based on the machine learning technique used by the researchers. The present review work will open the horizon for the researchers working on the machine learning based prediction of the compressive strength of concrete by providing the recommendations and benefits and drawbacks associated with each model as determining the compressive strength of concrete practically is a laborious and time-consuming task.

Corrosion of reinforcing bars in reinforced concrete structures due to chloride attack in environments containing chloride ions is one of the most important factors in the destruction of concrete structures. According to the abundant reports that the corrosion rate around the repair area has increased due to the macro-cell current known as the incipient anode, it is necessary to understand the effective parameters. The main objective of this paper is to investigate the effect of the kinetic parameters of corrosion including the cathodic Tafel slope, exchange current density, and equilibrium potential in repair materials on the total corrosion rate and maximum corrosion rate in the patch repair system. With the numerical simulation of the patch repair system and concerning the effect of parameters such as electromotive force (substrate concrete activity level), length of repair area, and resistivity of substrate and repair concrete, and with constant other parameters, the sensitivity of the macro-cell current caused by changes in the kinetic parameters of corrosion of the repairing materials has been investigated. The results show that the maximum effect on the macro-cell current values occurred with the change of cathodic Tafel slope, and the effect change of exchange current density and the equilibrium potential is almost the same. In the low repair extant and low resistivity of the repairing materials, with the increase in the electromotive force (degree of substrate concrete activity) of the patch repair system, the sensitivity of the total corrosion current reduces with the reduction in the cathode Tafel slope. The overall corrosion current will be very sensitive to changes in the kinetic parameters of corrosion. The change in the cathodic Tafel slope from 0.16 to 0.12 V/dec and in 300 mV the electromotive force will translate into an increase of 200% of the total corrosion current. While the percentage of this change in currency density and equilibrium potential is 53 and 43 percent, respectively. Moreover, by increasing the electro-motive force, the sensitivity of the total corrosion current decreases or becomes constant. The maximum corrosion does not change significantly based on the modification of the corrosion kinetic parameters and the modification will not affect the maximum corrosion in the repair system. Given that the macro-cell current in addition to the repair geometry is influenced by the sections of reactions of cathodic, anodic, and ohmic drop in repair and base concrete materials, in different parameters depending on the dominance of each section, the sensitivity of the total current and maximum corrosion in each scenario will be different.

An analysis of the Poisson's ratios influence of single walled carbon nanotubes (SWCNTs) based on Sander's shell theory is carried out. The effect of Poisson's ratio, boundary conditions and different armchairs SWCNTs is discussed and studied. The Galerkin's method is applied to get the eigen values in matrix form. The obtained results shows that, the decrease in ratios of Poisson, the frequency increases. Poisson's ratio directly measures the deformation in the material. A high Poisson's ratio denotes that the material exhibits large elastic deformation. Due to these deformation frequencies of carbon nanotubes increases. The frequency value increases with the increase of indices of single walled carbon nanotubes. The prescribe boundary conditions used are simply supported and clamped simply supported. The Timoshenko beam model is used to compare the results. The present method should serve as bench mark results for agreeing the results of other models, with slightly different value of the natural frequencies.

The seismic safety of the shear wall structure can be assessed through seismic fragility analysis, which requires high computational costs in estimating seismic demands. Accordingly, machine learning methods have been applied to such fragility analyses in recent years to reduce the numerical analysis cost, but it still remains a challenging task. Therefore, this study uses the ensemble machine learning method to present an improved framework for developing a more accurate seismic demand model than the existing ones. To this end, a rank-based selection method that enables determining an excellent model among several single machine learning models is presented. In addition, an index that can evaluate the degree of overfitting/underfitting of each model for the selection of an excellent single model is suggested. Furthermore, based on the selected single machine learning model, we propose a method to derive a more accurate ensemble model based on the bagging method. As a result, the seismic demand model for which the proposed framework is applied shows about 3-17% better prediction performance than the existing single machine learning models. Finally, the seismic fragility obtained from the proposed framework shows better accuracy than the existing fragility methods.

Concrete is the most widely used building material, with various types including high- and ultra-high-strength, reinforced, normal, and lightweight concretes. However, accurately predicting concrete properties is challenging due to the geotechnical design code's requirement for specific characteristics. To overcome this issue, researchers have turned to new technologies like machine learning to develop proper methodologies for concrete specification. In this study, we propose a highly accurate deep learning-based predictive model to investigate the compressive strength (UCS) of lightweight concrete with natural aggregates (pumice). Our model was implemented on a database containing 249 experimental records and revealed that water, cement, water-cement ratio, fine-coarse aggregate, aggregate substitution rate, fine aggregate replacement, and superplasticizer are the most influential covariates on UCS. To validate our model, we trained and tested it on random subsets of the database, and its performance was evaluated using a confusion matrix and receiver operating characteristic (ROC) overall accuracy. The proposed model was compared with widely known machine learning methods such as MLP, SVM, and DT classifiers to assess its capability. In addition, the model was tested on 25 laboratory UCS tests to evaluate its predictability. Our findings showed that the proposed model achieved the highest accuracy (accuracy=0.97, precision=0.97) and the lowest error rate with a high learning rate (R2=0.914), as confirmed by ROC (AUC=0.971), which is higher than other classifiers. Therefore, the proposed method demonstrates a high level of performance and capability for UCS predictions.

Fast-built construction is a key feature for successful applications of precast concrete (PC) moment frame system in recent construction practices. To this end, by introducing some unique splicing details in precast connections, especially between PC columns including panel zones, use of temporary supports and bracings can be minimized based on their self-sustaining nature. In addition, precast wide beams are commonly adopted for better economic feasibility. In this study, three self-sustaining precast concrete (PC) wide beam-column connection specimens were fabricated and tested under reversed cyclic loadings, and their seismic performances were quantitatively evaluated in terms of strength, ductility, failure modes, energy dissipation and stiffness degradation. Test results were compared with ASCE 41-17 nonlinear modeling curves and its corresponding acceptance criteria. On this basis, an improved macro modeling method was explored for a more accurate simulation. It appeared that all the test specimens fully satisfy the acceptance criteria, but the implicit joint model recommended in ASCE 41-17 tends to underestimate the joint shear stiffness of PC wide beam-column connection. While, the explicit joint model along with concentrated plastic hinge modeling technique is able to present better accuracy in simulating the cyclic responses of PC wide beam-column connections.