Search

Portland cement (PC) is considered the most energy-intensive building material and contributes to around 10% of global warming. It exacerbates global warming and climate change, which have a harmful environmental impact. Efforts are being made to produce sustainable and green concrete as an alternative to PC concrete. As a result, developing a more sustainable strategy and eco-friendly materials to replace ordinary concrete has become critical. Many studies on geopolymer concrete, which has equal or even superior durability and strength compared to traditional concrete, have been conducted for this purpose by many researchers. Geopolymer concrete (GPC) has been developed as a possible new construction material for replacing conventional concrete, offering a clean technological choice for long-term growth. Over the last few decades, geopolymer concrete has been investigated as a feasible green construction material that can reduce CO2 emissions because it uses industrial wastes as raw materials. GPC has proven effective for structural applications due to its workability and analogical strength compared to standard cement concrete. This review article discusses the engineering properties and microstructure of GPC and shows its merits in construction applications with some guidelines and suggestions recommended for both the academic community and the industrial sector. This literature review also demonstrates that the mechanical properties of GPC are comparable and even sometimes better than those of PC concrete. Moreover, the microstructure of GPC is significantly different from that of PC concrete microstructure and can be affected by many factors.

Rock deformation is considered one of the essential rock properties used in designing and constructing rock-based structures, such as tunnels and slopes. This study applied two well-established ensemble techniques, including boosting and bagging, to the artificial neural networks and decision tree methods for predicting the Young’s modulus of rock material. These techniques were applied to a dataset comprising 45 data samples from a mountain range in Malaysia. The final input variables of these models, including p-wave velocity, interlocking coarse-grained crystals of quartz, dry density, and Mica, were selected through a likelihood ratio test. In total, six models were developed: standard artificial neural networks, boosted artificial neural networks, bagged artificial neural networks, classification and regression trees, extreme gradient boosting trees (as a boosted decision tree), and random forest (as a bagging decision tree). The performance of these models was appraised utilizing correlation coefficient (R), mean absolute error (MAE), and lift chart. The findings of this study showed that, firstly, extreme gradient boosting trees outperformed all models developed in this study; secondly, boosting models outperformed the bagging models.

Ground vibration is one of the most unfavourable environmental effects of blasting activities, which can cause serious damage to neighboring homes and structures. As a result, effective forecasting of their severity is critical to controlling and reducing their recurrence. There are several conventional vibration predictor equations available proposed by different researchers but most of them are based on only two parameters, i.e., explosive charge used per delay and distance between blast face to the monitoring point. It is a well-known fact that blasting results are influenced by a number of blast design parameters, such as burden, spacing, powder factor, etc. but these are not being considered in any of the available conventional predictors and due to that they show a high error in predicting blast vibrations. Nowadays, artificial intelligence has been widely used in blast engineering. Thus, three artificial intelligence approaches, namely Gaussian process regression (GPR), extreme learning machine (ELM) and backpropagation neural network (BPNN) were used in this study to estimate ground vibration caused by blasting in Shree Cement Ras Limestone Mine in India. To achieve that aim, 101 blasting datasets with powder factor, average depth, distance, spacing, burden, charge weight, and stemming length as input parameters were collected from the mine site. For comparison purposes, a simple multivariate regression analysis (MVRA) model as well as, a nonparametric regression-based technique known as multivariate adaptive regression splines (MARS) was also constructed using the same datasets. This study serves as a foundational study for the comparison of GPR, BPNN, ELM, MARS and MVRA to ascertain their respective predictive performances. Eighty-one (81) datasets representing 80% of the total blasting datasets were used to construct and train the various predictive models while 20 data samples (20%) were utilized for evaluating the predictive capabilities of the developed predictive models. Using the testing datasets, major indicators of performance, namely mean squared error (MSE), variance accounted for (VAF), correlation coefficient (R) and coefficient of determination (R2) were compared as statistical evaluators of model performance. This study revealed that the GPR model exhibited superior predictive capability in comparison to the MARS, BPNN, ELM and MVRA. The GPR model showed the highest VAF, R and R2 values of 99.1728%, 0.9985 and 0.9971 respectively and the lowest MSE of 0.0903. As a result, the blast engineer can employ GPR as an effective and appropriate method for forecasting blast-induced ground vibration.

Due to the different challenges in rock sampling and in measuring their thermal conductivity (TC) in the field and laboratory, the determination of the TC of rocks using non-invasive methods is in demand in engineering projects. The relationship between TC and non-destructive tests has not been well-established. An investigation of the most important variables affecting the TC values for rocks was conducted in this study. Currently, the black-boxed models for TC prediction are being replaced with artificial intelligence-based models, with mathematical equations to fill the gap caused by the lack of a tangible model for future studies and developments. In this regard, two models were developed based on which gene expression programming (GEP) algorithms and non-linear multivariable regressions (NLMR) were utilized. When comparing the performances of the proposed models to that of other previously published models, it was revealed that the GEP and NLMR models were able to produce more accurate predictions than other models were. Moreover, the high value of R-squared (equals 0.95) for the GEP model confirmed its superiority.

Determining the fracture toughness of rock materials is a challenging, costly, and time-consuming task, as fabricating a sharp crack in rock specimens will lead to failure of the specimen, and preparing specimens for determining the rock fracture toughness requires special equipment. In this paper, the relationship between mode I fracture toughness (KIC) with the rock index properties, mineralogy, and petrography of limestone is investigated using simple nonlinear and simple/multiple linear regression analyses to provide alternative methods for estimating the fracture toughness of limestones. The cracked chevron notched Brazilian disk (CCNBD) method was applied to 30 limestones with different petrographic and mineralogical characteristics under both dry and saturated conditions. Moreover, the index properties of the same rocks, including the density, porosity, electrical resistivity, P and S wave velocities, Schmidt rebound hardness, and point load index, were determined. According to the statistical analyses, a classification based on the petrography of the studied rocks was required for predicting the fracture toughness from index properties. By classifying the limestones based on petrography, reliable relationships with high correlations can be introduced for estimating the fracture toughness of different limestones using simple tests.

The safe disposal of an enormous amount of waste glass (WG) in several countries has become a severe environmental issue. In contrast, concrete production consumes a large amount of natural resources and contributes to environmental greenhouse gas emissions. It is widely known that many kinds of waste may be utilized rather than raw materials in the field of construction materials. However, for the wide use of waste in building construction, it is necessary to ensure that the characteristics of the resulting building materials are appropriate. Recycled glass waste is one of the most attractive waste materials that can be used to create sustainable concrete compounds. Therefore, researchers focus on the production of concrete and cement mortar by utilizing waste glass as an aggregate or as a pozzolanic material. In this article, the literature discussing the use of recycled glass waste in concrete as a partial or complete replacement for aggregates has been reviewed by focusing on the effect of recycled glass waste on the fresh and mechanical properties of concrete.

Applications related to alkali-activated materials (AAMs) have received much attention due to their excellent mechanical properties and low-energy production. Although much research has focused on developing AAMs, their application is still limited. One of the primary reasons is the efflorescence. Not only does efflorescence affect the material aesthetics, but it also affects the mechanical performance, leading to a decrease in material quality. This paper first summarizes the current research on AAMs efflorescence. The formation process of efflorescence is divided into three parts: alkaline cation leaching, air carbonation, and efflorescence formation. Furthermore, the influences caused by different factors, including raw materials, curing conditions, AAMs modalities, etc., on the efflorescence are proposed. This paper highlights the solutions for efflorescence by avoiding free alkaline cation leaching and preventing air carbonation. The advantages and disadvantages of efflorescence are discussed in-depth, showing that it can be exploited under certain conditions, such as in wastewater treatment. This paper has important implications for the practical preparation and application of AAMs.

SAC (sulfoaluminate cement) has become a research hotspot as a low-carbon ecological cement. In addition, multi-walled carbon nanotubes have good thermal, mechanical, and electrical properties and can serve as excellent nano-reinforced cement-based fillers. This study explored the dispersion of carbon nanotubes (CNTs) and researched the effect of CNTs on the mechanical properties, hydration process, hydration products, and microstructure of SAC paste, and the mechanism of CNT-enhanced SAC paste was revealed. The results showed that the mechanical properties of SAC paste were significantly improved after the addition of CNTs. When the CNT content was 0.05%, 0.1%, and 0.15%, the compressive strength after 28 d was increased by 13.2%, 18.3%, and 22.5%, respectively; compared with the C0 group (without CNTs), the flexural strength increased by 8.2%, 11.3%, and 14.4%, respectively. The addition of CNTs accelerated the hydration process of SAC paste. Due to the adsorption effect and nucleation effect of CNTs, more hydration products were generated, filling the matrix’s pores and improving its compactness. The mechanism of CNTs enhanced SAC paste was revealed. CNTs and hydration products co-filled the pores, including AFt (ettringite) and AH3 (gibbsite). CNTs improve the mechanical properties of SAC paste through filling, bridging, crack bending, deflection, pulling out, and pulling off.

In deep foundations, the pile group and the pile raft are generally used. To date, the contribution of the raft is not taken into account in the design, even when the raft is in contact with the soil and the whole system is therefore considered to work as a pile group foundation. In a combined pile raft system, the raft takes a considerable portion of the applied load, depending upon the number of piles, the spacing to diameter ratio of the piles, and the length to diameter ratio. In this paper, an experimental investigation is carried out to study the response of small-scale pile group and piled raft models with a varying number of piles subjected to both vertical and lateral loads. Additionally, the response mechanism of these models to both types of loads is also studied. A comparison was made between these models. It was found that, unlike the pile group, the piled raft provides considerably high stiffness to both types of loads, and the difference between the stiffness of both systems decreases as the number of piles increases. By comparing the response of the piled raft and the pile group with the same number of piles under the same vertical and lateral load, it was concluded that the piled raft response to the lateral and vertical loads was much stiffer than the pile group response. The lateral deflection and the vertical settlement of the piled raft were less than those of the pile group with the same pile configuration. This effective response of the piled raft to the vertical and lateral loads was due to the raft contribution in resisting the vertical and lateral loads. Moreover, with the increase in the number of piles, the vertical and lateral contribution of the raft decreases.

Sulfoaluminate cement (SAC) is a low carbon ecological cement with good durability and is widely used in various projects. In addition, graphene nanoplates (GNPs) have excellent thermal, electrical, and mechanical properties and are excellent nano-filler. However, the hydration behavior of GNPs on SAC is still unclear. In this paper, the effect of GNPs on SAC hydration was investigated by isothermal calorimetry, and the hydration kinetic model and hydration kinetic equation of SAC was established, explaining the differences in cement hydration processes with and without GNPs on SAC based on a hydration kinetic model. Results indicate that the hydration exotherm of SAC mainly includes five stages: the initial stage, the induction stage, the acceleration stage, the deceleration stage, and the stable stage. The addition of GNPs promoted the hydration exotherm of SAC and accelerated the hydration reaction. Different from the hydration reaction of Portland cement, the hydration reaction of SAC is mainly a diffusion–reaction process.

The international roughness index (IRI) can be employed to evaluate the smoothness of pavement. The previously proposed mechanical-empirical pavement design guide (MEPDG), which is used to model the IRI of joint plain concrete pavement (JPCP), has been modified in this study considering its disadvantage of low prediction accuracy. To improve the reliability of the prediction effect of the IRI for JPCP, this study compares the prediction accuracy of the IRI of JPCP by using the machine-learning methods of support vector machine (SVM), decision tree (DT), and random forest (RF), optimized by the hyperparameter of the beetle antennae search (BAS) algorithm. The results from the machine-learning process show that the BAS algorithm can effectively improve the effectiveness of hyperparameter tuning, and then improve the speed and accuracy of optimization. The RF model proved to be the one with the highest prediction accuracy among the above three models. Finally, this study analyzes the importance score of input variables to the IRI, and the results show that the IRI was proportional to all the input variables in this study, and the importance score of initial smoothness (IRII) and total joint faulting cumulated per km (TFAULT) were the highest for the IRI of JPCP.

Brittleness plays an important role in assessing the stability of the surrounding rock mass in deep underground projects. To this end, the present study deals with developing a robust evolutionary programming paradigm known as linear genetic programming (LGP) for estimating the brittleness index (BI). In addition, the bootstrap aggregate (Bagged) regression tree (BRT) and two efficient lazy machine learning approaches, namely local weighted linear regression (LWLR) and KStar approach, were examined to validate the LGP model. To the best of our knowledge, this is the first attempt to estimate the BI through the LGP model. A tunneling project in Pahang state, Malaysia, was investigated, and the requirement datasets were measured to construct the proposed models. According to the results from the testing phase, the LGP model yielded the best statistical indicators (R = 0.9529, RMSE = 0.4838, and IA = 0.9744) for modeling BI, followed by LWLR (R = 0.9490, RMSE = 0.6607, and IA = 0.9400), BRT (R = 0.9433, RMSE = 0.6875, and IA = 0.9324), and KStar (R = 0.9310, RMSE = 0.7933, and IA = 0.9095), respectively. In addition, the sensitivity analysis demonstrated that the dry density factor demonstrated the most effective prediction of BI.

This article is dedicated to investigating the properties of soil after its reinforcement with fiberglass elements through large-scale laboratory plate-load tests of various samples that varied in the numbers and lengths of the reinforcing elements. The investigation of the vertical elements considered the diameter increase at the bottom toe by using widening washers. The results were compared relative to each other and to the theoretical calculation results. The theoretical calculations for the settlements were undertaken based on the authors’ proposed method. The method considers the number, shape, area and material of the strengthening elements using a pre-proposed reinforcement area factor µ. This pre-established factor was calculated with reference to the elements’ geometry—the diameter of the vertical elements and the bottom’s washer diameter—which determined the reinforcement area. A comparison between the reinforced and reference soft sandy soil samples indicated a 25% increase in the deformation modulus after the reinforcement process at a pressure of 25 kPa. Samples with µ ranging from 1.20 to 1.43 were 55–65% stiffer than samples with µ equal to 0.69 at a pressure of 100 kPa. The comparative analysis of the calculated results and the actual laboratory PLT test results was adequate for use for further development.

In this study, the potential application of slag-fly ash-based geopolymers as stabilizers for soft soil in sulfate erosion areas was investigated to promote environmental protection and waste residue recycling. The changes in the physical and mechanical properties and microstructure characteristics of cement-stabilized soil/geopolymer-stabilized soil under sulfate erosion were comparatively studied through tests such as appearance change, mass change, strength development, and microscopic examination. The results show that the sulfate resistance of stabilized soil is significantly affected by the stabilizer type. In the sulfate environment, the cement-stabilized soil significantly deteriorates with erosion age due to the expansion stress induced by AFt, while the geopolymer-stabilized soil exhibits excellent sulfate resistance. The slag-fly ash ratio (10:0, 9:1, 8:2 and 7:3) is an important factor affecting the sulfate resistance of geopolymer-stabilized soils, and the preferred value occurs at 9:1 (G-2). When immersed for 90 d, the unconfined compressive strength value of G-2 is 7.13 MPa, and its strength retention coefficient is 86.6%. The N-A-S-H gel formed by the polymerization in the geopolymer contributes to hindering the intrusion of sulfate ions, thereby improving the sulfate resistance of stabilized soil. The research results can provide a reference for technology that stabilizes soil with industrial waste in sulfate erosion areas.

The present study aimed at evaluating the mechanical performance under bending loads of circular hollow sections of steel. Different bending tests have been carried out by applying two-point loads, to determine and examine the effects of the diameter, the thickness of the section, and the span of the beam on the performance of the steel tube. The effects of square opening and variation in the number of openings on the performance of these sections have also been examined. Ten samples of hollow circular beams of varying thickness (2 mm, 3 mm, and 6 mm), varying diameter (76.2 mm, 101.6 mm, and 219 mm), and varying span (1000 mm, 1500 mm, and 2000 mm) were fabricated and tested for pre-failure and post-failure stages. The dimensions of the reference specimen considered were 3 mm in thickness, 101.6 mm in diameter, and 1500 mm in span. The results have shown that on increasing the section thickness by 200%, ductility and bearing strength were enhanced by 58.04% and 81.75%, respectively. Meanwhile, decreasing the section thickness by 67%, ductility and bearing strength were reduced by 64.86% and 38.87%, respectively. Moreover, on increasing the specimen diameter and on decreasing span, a significant increase in bearing strength and stiffness was observed; however, ductility was reduced. Meanwhile, on increasing the span of the specimen, all the parameters observed, i.e., bearing strength, stiffness, and ductility, decreased. On observing the ultimate strength of each specimen with square opening, the ultimate strength was reduced by 17.88%, 19.71%, and 14.23% for one, two-, and three-square openings, respectively. Moreover, the ductility was significantly reduced by 72.40%, 67.71%, and 60.88% for one, two-, and three-square openings/apertures, respectively, and led to the sudden failure of these specimens. The local buckling failure dominated for specimens having a D/t ratio more than 50 and showed very negligible levels of ovalization of the cross-section. Local buckling failure was observed to be prevented after providing the circular rings in the specimen, since bearing strength increased compared with the specimen without rings.

Concrete is the most widely used material in construction. It has the characteristics of strong plasticity, good economy, high safety, and good durability. As a kind of structural material, concrete must have sufficient strength to resist various loads. At the same time, due to the brittleness of concrete, compressive strength is the most important mechanical property of concrete. To solve the disadvantages of the low efficiency of the traditional concrete compressive strength prediction methods, this study proposes a firefly algorithm (FA) and random forest (RF) hybrid machine-learning method to predict the compressive strength of concrete. First, a database is built based on the data of published articles. The dataset in the database contains eight input variables (cement, blast furnace slag, fly ash, water, superplasticizer, coarse aggregate, fine aggregate, and age) and one output variable (concrete compressive strength). Then, the correlation of the eight input variables was analyzed, and the results showed that there was no high correlation between the input variables; thus, they could be used as input variables to predict the compressive strength of concrete. Next, this study used the FA algorithm to optimize the hyperparameters of RF to obtain better hyperparameters. Finally, we verified that the FA and RF hybrid machine-learning model proposed in this study can predict the compressive strength of concrete with high accuracy by analyzing the R values and RSME values of the training set and test set and comparing the predicted value and actual value of the training set and test machine.

Ultrasonic pulse velocity (UPV) and rebound hammer tests are accepted as alternatives to destructive testing to determine the compressive strength, dynamic modulus of elasticity, and Poisson’s ratio, which are needed for structural design. Although much work has been conducted for plain concrete, the research data for fibre-reinforced concrete (FRC) is insufficient. In this regard, this study explains the correlations between compressive strength, rebound hammer, and UPV tests for plain concrete and FRC contains 0.25%, 0.50%, and 1.00% of 30 mm and 50 mm long steel fibres. A total of 78 concrete cube and beam specimens were tested by direct, semi-direct, and indirect UPV and rebound hammer test methods. The study found that the rebound hammer test is more suitable for measuring the compressive strength of matured FRC than young concrete. The UPV test revealed that the volume fraction does not, but the length of steel fibres does affect the UPV results by the direct test method. The UPV direct method has the highest velocity, approximately two times the indirect velocity in FRC. UPV measurements can be effectively used to determine the dynamic modulus of elasticity and Poisson’s ratio of FRC. The dynamic elastic modulus increases while the Poisson’s ratio decreases for the same steel fibre length when at increasing FRC fibre content. The results of this study will be significant for non-destructive evaluations of FRC, while additional recommendations for future studies are presented at the end of the paper.

The low tensile strain capacity and brittle nature of high-strength concrete (HSC) can be improved by incorporating steel fibers into it. Steel fibers’ addition in HSC results in bridging behavior which improves its post-cracking behavior, provides cracks arresting and stresses transfer in concrete. Using machine learning (ML) techniques, concrete properties prediction is an effective solution to conserve construction time and cost. Therefore, sophisticated ML approaches are applied in this study to predict the compressive strength of steel fiber reinforced HSC (SFRHSC). To fulfil this purpose, a standalone ML model called Multiple-Layer Perceptron Neural Network (MLPNN) and ensembled ML algorithms named Bagging and Adaptive Boosting (AdaBoost) were employed in this study. The considered parameters were cement content, fly ash content, slag content, silica fume content, nano-silica content, limestone powder content, sand content, coarse aggregate content, maximum aggregate size, water content, super-plasticizer content, steel fiber content, steel fiber diameter, steel fiber length, and curing time. The application of statistical checks, i.e., root mean square error (RMSE), determination coefficient (R2), and mean absolute error (MAE), was also performed for the assessment of algorithms’ performance. The study demonstrated the suitability of the Bagging technique in the prediction of SFRHSC compressive strength. Compared to other models, the Bagging approach was more accurate as it produced higher, i.e., 0.94, R2, and lower error values. It was revealed from the SHAP analysis that curing time and super-plasticizer content have the most significant influence on the compressive strength of SFRHSC. The outcomes of this study will be beneficial for researchers in civil engineering for the timely and effective evaluation of SFRHSC compressive strength.

The composite shear wall has various merits over the traditional reinforced concrete walls. Thus, several experimental studies have been reported in the literature in order to study the seismic behavior of composite shear walls. However, few numerical investigations were found in the previous literature because of difficulties in the interaction behavior of steel and concrete. This study aimed to present a numerical analysis of smart composite shear walls, which use an infilled steel plate and concrete. The study was carried out using the ANSYS software. The mechanical mechanisms between the web plate and concrete were investigated thoroughly. The results obtained from the finite element (FE) analysis show excellent agreement with the experimental test results in terms of the hysteresis curves, failure behavior, ultimate strength, initial stiffness, and ductility. The present numerical investigations were focused on the effects of the gap, thickness of infill steel plate, thickness of the concrete wall, and distance between shear studs on the composite steel plate shear wall (CSPSW) behavior. The results indicate that increasing the gap between steel plate and concrete wall from 0 mm to 40 mm improved the stiffness by 18% as compared to the reference model, which led to delay failures of this model. Expanding the infill steel plate thickness to 12 mm enhanced the stiffness and energy absorption with a ratio of 95% and 58%, respectively. This resulted in a gradual drop in the strength capacity of this model. Meanwhile, increasing concrete wall thickness to 150 mm enhanced the ductility and energy absorption with a ratio of 52% and 32%, respectively, which led to restricting the model and reduced lateral offset. Changing the distance between shear studs from 20% to 25% enhanced the ductility and energy absorption by about 66% and 32%, respectively.

Non-destructive tests (NDTs) represent one of the solutions that aid engineers in evaluating the strength of materials. However, the results obtained using such tests are still questionable as they may be affected by different factors. One of these factors is the presence of steel reinforcement in concrete. An experimental investigation is presented in this study to investigate the effect of the single reinforcement steel bar on ultrasonic pulse velocity (UPV). Seven concrete beams, one containing no steel and the other six beams containing varying bar diameter and cover thicknesses, were tested. UPV measurements were obtained using the indirect method and then modified to eliminate the effect of the steel bar. To provide the scientific evidence to give a reliable and reasonable solution, a statistical analysis was also conducted. The results show that a large bar diameter and a small cover thickness significantly influence the measured UPV. Measured UPV with a spacing between transducers up to 500 mm can effectively be used to predict the compressive strength of concrete after the modification of the initial UPV.

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.

Blasting is one of the primary aspects of the mining operations, and its environmental effects interfere with the safety of lives and property. Therefore, it is essential to accurately estimate the environmental impact of blasting, i.e., peak particle velocity (PPV). In this study, a regular random forest (RF) model was developed using 102 blasting samples that were collected from an open granite mine. The model inputs included six parameters, while the output is PPV. Then, to improve the performance of the regular RF model, five techniques, i.e., refined weights based on the accuracy of decision trees and the optimization of three metaheuristic algorithms, were proposed to enhance the predictive capability of the regular RF model. The results showed that all refined weighted RF models have better performance than the regular RF model. In particular, the refined weighted RF model using the whale optimization algorithm (WOA) showed the best performance. Moreover, the sensitivity analysis results revealed that the powder factor (PF) has the most significant impact on the prediction of the PPV in this project case, which means that the magnitude of the PPV can be managed by controlling the size of the PF.

Cement-based materials are widely used in construction engineering because of their excellent properties. With the continuous improvement of the functional requirements of building infrastructure, the performance requirements of cement-based materials are becoming higher and higher. As an important property of cement-based materials, compressive strength is of great significance to its research. In this study, a Random Forests (RF) and Firefly Algorithm (FA) hybrid machine learning model was proposed to predict the compressive strength of metakaolin cement-based materials. The database containing five input parameters (cement grade, water to binder ratio, cement-sand ratio, metakaolin to binder ratio, and superplasticizer) based on 361 samples was employed for the prediction. In this model, FA was used to optimize the hyperparameters, and RF was used to predict the compressive strength of metakaolin cement-based materials. The reliability of the hybrid model was verified by comparing the predicted and actual values of the dataset. The importance of five variables was also evaluated, and the results showed the cement grade has the greatest influence on the compressive strength of metakaolin cement-based materials, followed by the water-binder ratio.

Cement-slag concrete has become one of the most widely used building materials considering its economical advantage and satisfying uniaxial compressive strength (UCS). In this study, an AI-based method for cement-slag concrete design was developed based on the balance of economic and mechanical properties. Firstly, the hyperparameters of random forest (RF), decision tree (DT), and support vector machine (SVM) were tuned by the beetle antennae search algorithm (BAS). The results of the model evaluation showed the RF with the best prediction effect on the UCS of concrete was selected as the objective function of UCS optimization. Afterward, the objective function of concrete cost optimization was established according to the linear relationship between concrete cost and each mixture. The obtained results showed that the weighted method can be used to construct the multi-objective optimization function of UCS and cost for cement-slag concrete, which is solved by the multi-objective beetle antennae search (MOBAS) algorithm. An optimal concrete mixture ratio can be obtained by Technique for Order Preference by Similarity to Ideal Solution. Considering the current global environment trend of “Net Carbon Zero”, the multi-objective optimization design should be proposed based on the objectives of economy-carbon emission-mechanical properties for future studies.

Circular hollow steel tube columns are widely used in high-rise buildings and bridges due to their ductility and lower weight compared to reinforced concrete. The use of this type of steel section has several advantages over using reinforced concrete members. The present study investigates the bending behavior of steel circular hollow sections when subjected to bending loads. The variations in material characteristics with regard to position along the cross-section of a steel tube member is first considered in this experimental study, providing for a more accurate definition of the material behavior in the model. A supported beam tested by two-point loads is the loading type that is used to study the bending performance of steel tubes. Ten circular hollow beam specimens were prepared and tested up to and post the failure stage with the following dimensions: thickness (2, 3, and 6 mm), diameter (76.2, 101.6, and 219 mm), and span (1000, 1500, and 2000 mm). A finite element analysis has been conducted for these ten specimens using the ANSYS program. The finite element model is compared to experimentally obtained data to verify that both local and global behaviors are correctly considered. The load-deflection results of this analysis showed a good agreement with the experimental results. A parametric study also was performed that considered two variables, which were the effect of the presence of circular rings and the change of opening location in the length direction on the specimens’ behavior. This study showed that the presence of the circular rings in the specimen led to an increase in its ultimate strength (of 53.24%) compared with the non-presence of these rings. In contrast, the presence of openings at 30, 40, and 50% from the specimen length reduced the strength capacity by 8.76, 14.23, and 17.88%, respectively.

During design and construction of buildings, the employed materials can substantially impact the structures’ performance. In composite columns, the properties and performance of concrete and steel have a significant influence on the behavior of structure under various loading conditions. In this study, two metaheuristic algorithms, particle swarm optimization (PSO) and competitive imperialism algorithm (ICA), were combined with the artificial neural network (ANN) model to predict the bearing capacity of the square concrete-filled steel tube (SCFST) columns. To achieve this objective and investigate the performance of optimization algorithms on the ANN, one of the most extensive datasets of pure SCFST columns (with 149 data samples) was used in the modeling process. In-depth and detailed predictive modeling of metaheuristic-based models was conducted through several parametric investigations, and the optimum factors were designed. Furthermore, the capability of these hybrid models was assessed using robust statistical matrices. The results indicated that PSO is stronger than ICA in finding optimum weights and biases of ANN in predicting the bearing capacity of the SCFST columns. Therefore, each column and its bearing capacity can be well-predicted using the developed metaheuristic-based ANN model.

This study investigates the mechanical and durability properties of fly ash-based engineered cementitious composites (ECC). The effect of various mineral additions, such as wheat husk ash (WHA), rice husk ash (RHA), glass powder (GP), and fibrillated polypropylene (PP) fibers, on mechanical performance, water absorption, and porosity was investigated. Furthermore, the durability of ECC specimens was assessed in terms of sorptivity, acid/sulfate attacks, electric resistivity (ER), rapid chloride penetration (RCPT), and ultrasonic pulse velocity (UPV). The results revealed higher mechanical strength, UPV, and ER values for RHA-based ECC. After 180 days of immersion in acid and sulfate solutions, RHA-based ECC showed a lower loss in compressive strength (23.21% and 1.07% in HCl and Na2SO4, respectively) relative to the control mix (44% and 7% in HCl and Na2SO4, respectively). Moreover, analytical characterizations such as X-ray diffraction (XRD), Fourier transform infrared (FTIR), Scanning Electron Microscopy (SEM), and Energy dispersive X-ray (EDX) analyses were also carried out to corroborate the mechanical and durability properties of ECC.

Fiber-reinforced polymer (FRP) has several benefits, in addition to excellent tensile strength and low self-weight, including corrosion resistance, high durability, and easy construction, making it among the most optimum options for concrete structure restoration. The bond behavior of the FRP-concrete (FRPC) interface, on the other hand, is extremely intricate, making the bond strength challenging to estimate. As a result, a robust modeling framework is necessary. In this paper, data-driven hybrid models are developed by combining state-of-the-art population-based algorithms (bald eagle search (BES), dynamic fitness distance balance-manta ray foraging optimization (dFDB-MRFO), RUNge Kutta optimizer (RUN)) and artificial neural networks (ANN) named “BES-ANN”, “dFDB-MRFO -ANN”, and “RUN-ANN” to estimate the FRPC interfacial-bond strength accurately. The efficacy of these models in predicting bond strength is examined using an extensive database of 969 experimental samples. Compared to the BES-ANN and dFDB-MRFO models, the RUN-ANN model better estimates the interfacial-bond strength. In addition, the SHapley Additive Explanations (SHAP) approach is used to help interpret the best model and examine how the features influence the model’s outcome. Among the studied hybrid models, the RUN-ANN algorithm is the most accurate model with the highest coefficient of determination (R2 = 92%), least mean absolute error (0.078), and least coefficient of variation (18.6%). The RUN-ANN algorithm also outperformed mechanics-based models. Based on SHAP and sensitivity analysis method, the FRP bond length and width contribute more to the final prediction results.

This article is dedicated to developing a ground improvement technique using vertically oriented reinforcement elements prefabricated utilizing fiberglass pultruded pipe and helical shape wideners at the bottom toe. Structures of the prefabricated helical micropiles varied by the length and cross-section area introduced into the soil massive as reinforcing bearing elements. The effect of the reinforcements geometry variation was investigated through a reinforcement factor (µ), based on which a calculation method for measuring settlement of reinforced soil has been previously developed Full-scale field plate load tests were performed before and after reinforcing the soil to investigate the changes in the soil stiffness after the reinforcement process. Comparative analysis between the reinforced and reference soft sandy soil indicates an average increase in the deformation properties of the fiber reinforced soils by 8%, 30%, 63% at the applied pressures of 100, 300, and 550 kPa, respectively. The influence of the fiber reinforced polymers (FRP) geometrical properties on the final composite settlement was determined. A comparative analysis of the calculated and the actual plate load tests results reveals that the previously proposed settlement calculation method is adequate for further development.

Construction and demolition (C&D) waste was considered as zero value materials and, as a result, most C&D waste materials ended up in landfills, eventually constituting environmental issues. Therefore, it is important to explore the potential of such C&D waste materials for concrete production. Thus, this research effort aims to find a new method to improve sustainable concrete properties exposed to elevated temperatures at the lowest costs and identify the relationship between temperature change and a change in colour in a heat-exposed concrete structure. Therefore, this study explored the behaviour of three types of concrete: plain concrete (PC), waste ceramic optimal concrete (WOC), and waste ceramic optimal concrete reinforced by hybrid fibre (WOC-Hybrid) in ambient and elevated temperature. The study shows that colour change in a concrete structure exposed to high temperature has a consistent relationship, where it has been found that the colour alteration is of great interest because its appearance usually coincides with the onset of a significant loss of concrete strength as a result of elected temperatures. Overall, it can be considered that waste ceramic materials reinforced by hybrid fibres can be used for concrete production, and by doing so, the negative impact of these wastes on the environment can be controlled as well as fortify the mechanical properties.

Waste ceramic concrete (WOC) made from waste ceramic floor tiles has several economic and environmental benefits. Fire is one of the most common disasters in buildings, and WOC is a brittle construction material; therefore, the mechanical properties of WOC structures under high temperatures should be considered. According to previous studies, hybrid fiber can further reduce damage to concrete under high temperatures. Meanwhile, crack width and propagation are among the key characteristics of concrete materials that need to be considered, but few studies have focused on their behavior when subjected to elevated temperatures. The new concrete materials proposed by the authors are WOC and WOC-Hybrid. WOC was prepared with Natural Coarse Aggregates (NCA), Natural Fine Aggregate (NFA), Ordinary Portland Cement (OPC 43 grade), and ceramic waste tiles with 20% replacements for coarse aggregates, 10% replacements for fine aggregates, and 10% replacement for cement. In contrast, WOC-Hybrid was prepared with the addition of hybrid fiber (1% crimped steel fiber and 1% polyvinyl alcohol fiber) in WOC. The specimens were exposed to temperatures of 100–300 °C, and then the specimens were tested for tensile and compressive strength. The present study aims to find a new method to improve concrete resistance to elevated temperatures at the lowest costs by experimental and computational analysis via machine learning models. The application of machine learning models such as artificial neural networks (ANN) and multiple linear regression (MLR) was employed in this study to predict the compressive and tensile strength of concrete. The linear coefficient correlation (R2) and mean square error (MSE) were evaluated to investigate the performance of the models. Based on the experimental analysis, the results show that the effect of hybrid fiber on the crack width and propagation is greater than that on the crack width and propagation of WOC and PC after exposure to high temperatures. However, the enhanced effect of hybrid fiber on the mechanical properties, rack width, and propagation decreases after subjecting it to a high-temperature treatment, owing to the melting and ignition of hybrid fibers at high temperatures. Regarding the computational analysis, it was found that the developed MLR model shows higher efficiency than ANN in predicting the compressive and tensile strength of PC, WOC, and WOC-Hybrid concrete.

The mechanical behavior of the rockfill materials (RFMs) used in a dam’s shell must be evaluated for the safe and cost-effective design of embankment dams. However, the characterization of RFMs with specific reference to shear strength is challenging and costly, as the materials may contain particles larger than 500 mm in diameter. This study explores the potential of various kernel function-based Gaussian process regression (GPR) models to predict the shear strength of RFMs. A total of 165 datasets compiled from the literature were selected to train and test the proposed models. Comparing the developed models based on the GPR method shows that the superlative model was the Pearson universal kernel (PUK) model with an R-squared (R2) of 0.9806, a correlation coefficient (r) of 0.9903, a mean absolute error (MAE) of 0.0646 MPa, a root mean square error (RMSE) of 0.0965 MPa, a relative absolute error (RAE) of 13.0776%, and a root relative squared error (RRSE) of 14.6311% in the training phase, while it performed equally well in the testing phase, with R2 = 0.9455, r = 0.9724, MAE = 0.1048 MPa, RMSE = 0.1443 MPa, RAE = 21.8554%, and RRSE = 23.6865%. The prediction results of the GPR-PUK model are found to be more accurate and are in good agreement with the actual shear strength of RFMs, thus verifying the feasibility and effectiveness of the model.