Construction and demolition waste (CDW) are the largest waste products in the world today and competes as a viable recycled additive material in place of natural aggregates. Due to the increase in compressive strength of different mix proportions of CDW, it is also considered for reuse in concrete and subbase construction. This study shows the effect of CDW in expansive soil stabilization. The chemical and mechanical properties of these materials have shown that they are capable of developing compressive strength properties for replacement of cement with significant reduction in carbon emission. The inherent compositional properties of recycled CDW compared in this review suggests that CDW have good filler properties in highly expansive soils. Mixtures of crushed brick and recycled aggregates characterised based on chemical properties of different replacement ratios suggests that CDW of good-quality aggregates reduces swell potential of expansive soils and increased mechanical strength in pavement construction.

To research the axial compression behavior of steel reinforced recycled concrete (SRRC) short columns confined by carbon fiber reinforced plastics (CFRP) strips, nine scaled specimens of SRRC short columns were fabricated and tested under axial compression loading. Subsequently, the failure process and failure modes were observed, and load-displacement curves as well as the strain of various materials were analyzed. The effects on the substitution percentage of recycled coarse aggregate (RCA), width of CFRP strips, spacing of CFRP strips and strength of recycled aggregate concrete (RAC) on the axial compression properties of columns were also analyzed in the experimental investigation. Furthermore, the finite element model of columns which can consider the adverse influence of RCA and the constraint effect of CFRP strips was founded by ABAQUS software and the nonlinear parameter analysis of columns was also implemented in this study. The results show that the first to reach the yield state was the profile steel in the columns, then the longitudinal rebars and stirrups yielded successively, and finally RAC was crushed as well as the CFRP strips was also broken. The replacement rate of RCA has little effect on the columns, and with the substitution rate of RCA from 0 to 100%, the bearing capacity of columns decreased by only 4.8%. Increasing the CFRP strips width or decreasing the CFRP strips spacing could enhance the axial bearing capacity of columns, the maximum increase was 10.5% or 11.4%, and the ductility of columns was significantly enhanced. Obviously, CFRP strips are conducive to enhance the axial bearing capacity and deformation capacity of columns. On this basis, considering the restraint effect of CFRP strips and the adverse effects of RCA, the revised formulas for calculating the axial bearing capacity of SRRC short columns confined by CFRP strips were proposed.

In this study, finite element (FE) analysis is utilized to investigate the shear capacity of reinforced concrete (RC) beams strengthened with embedded through-section (ETS) bars. Effects of critical variables on the beam shear strength, including the compressive strength of concrete, stiffness ratio between ETS bars and steel stirrups, and use of ETS strengthening system alone, are parametrically investigated. A promising method based on the bond mechanism between ETS strengthening and concrete is then proposed for predicting the shear resistance forces of the strengthened beams. An expression for the maximum bond stress of the ETS bars to concrete is developed. This new expression eliminates the difficulty in the search and selection of appropriate bond parameters from adhesion tests. The results obtained from the FE models and analytical models are validated by comparison with those measured from the experiments. Consequently, the model proposed in this study demonstrates better performance and more accuracy for prediction of the beam shear-carrying capacity than those of existing models. The results obtained from this study can also serve researchers and engineers in selection of the proper shear strength models for design of ETS-strengthened RC beams.

The behavior of rock masses is influenced by a variety of forces, with measurement of stress and strain playing the most critical roles in assessing deformation. The laboratory test for determining strain at each location within rock samples is expensive and difficult but rock strain data are important for predicting failure of rock material. Many researchers employ AI technology in order to solve these difficulties. AI algorithms such as gradient boosting machine (GBM), support vector regression (SVR), random forest (RF), and group method of data handling (GMDH) are used to efficiently estimate the strain at every point within a rock sample. Additionally, the ensemble unit (EnU) may be utilized to evaluate rock strain. In this study, 3000 experimental data are used for the purpose of prediction. The obtained strain values are then evaluated using various statistical parameters and compared to each other using EnU. Ranking analysis, stress-strain curve, Young’s modulus, Poisson’s ratio, actual vs. predicted curve, error matrix and the Akaike’s information criterion (AIC) values are used for comparing models. The GBM model achieved 98.16% and 99.98% prediction accuracy (in terms of values of R²) in the longitudinal and lateral dimensions, respectively, during the testing phase. The GBM model, based on the experimental data, has the potential to be a new option for engineers to use when assessing rock strain.

The failure criteria of practical soil mass are very complex, and have significant influence on the safety factor of slope stability. The Coulomb strength criterion and the power-law failure criterion are classically simplified. Each one has limited applicability owing to the noticeable difference between calculated predictions and actual results in some cases. In the work reported here, an analysis method based on the least square support vector machine (LSSVM), a machine learning model, is purposefully provided to establish a complex nonlinear failure criterion via iteration computation based on strength test data of the soil, which is of more extensive applicability to many problems of slope stability. In particular, three evaluation indexes including coefficient of determination, mean absolute percentage error, and mean square error indicate that fitting precision of the machine learning-based failure criterion is better than those of the linear Coulomb criterion and nonlinear power-law criterion. Based on the proposed LSSVM approach to determine the failure criterion, the limit equilibrium method can be used to calculate the safety factor of three-dimensional slope stability. Analysis of results of the safety factor of two three-dimensional homogeneous slopes shows that the maximum relative errors between the proposed approach and the linear failure criterion-based method and the power-law failure criterion-based method are about 12% and 7%, respectively.

The Limit Equilibrium Method (LEM) is commonly used in traditional slope stability analyses, but it is time-consuming and complicated. Due to its complexity and nonlinearity involved in the evaluation process, it cannot provide a quick stability estimation when facing a large number of slopes. In this case, the convolutional neural network (CNN) provides a better alternative. A CNN model can process data quickly and complete a large amount of data analysis in a specific situation, while it needs a large number of training samples. It is difficult to get enough slope data samples in practical engineering. This study proposes a slope database generation method based on the LEM. Samples were amplified from 40 typical slopes, and a sample database consisting of 20000 slope samples was established. The sample database for slopes covered a wide range of slope geometries and soil layers’ physical and mechanical properties. The CNN trained with this sample database was then applied to the stability prediction of 15 real slopes to test the accuracy of the CNN model. The results show that the slope stability prediction method based on the CNN does not need complex calculation but only needs to provide the slope coordinate information and physical and mechanical parameters of the soil layers, and it can quickly obtain the safety factor and stability state of the slopes. Moreover, the prediction accuracy of the CNN trained by the sample database for slope stability analysis reaches more than 99%, and the comparisons with the BP neural network show that the CNN has significant superiority in slope stability evaluation. Therefore, the CNN can predict the safety factor of real slopes. In particular, the combination of typical actual slopes and generated slope data provides enough training and testing samples for the CNN, which improves the prediction speed and practicability of the CNN-based evaluation method in engineering practice.

Because of favorable mechanical properties, deformation resistance and being conducive to environmental protection, honeycomb fabricated plastic pavement slabs are highly recommended these years. At present, most studies focus on the performance of plastic materials, however, the dimension optimization of fabricated plastic pavement slab is rarely mentioned. In this paper, an optimized geometry of the honeycomb pavement slab was determined through finite element analysis. Mechanical response of honeycomb slabs with different internal dimensions and external dimensions were explored. Several dimension factors were taken into consideration including the side length, rib thickness, the thickness of both top and bottom slabs of honeycomb structure and the length, the width and the thickness of the fabricated plastic slab. The results showed that honeycomb pavement slab with 6 cm bottom slab, 12 cm top slab,18 cm side length and 6 cm rib thickness is recommended, additionally, an external dimension of 4 m × 4 m × 0.45 m is suggested. Then, the mechanical responses of this optimized fabricated plastic slab were further investigated. Significance of different influencing factors, including wheel load, elastic modulus of plastic material, base layer thickness, soil foundation modulus and base layer modulus were ranked.

The newly-built single-level rail-cum-road bridge brings the issue of the aerodynamic impact of train-induced wind on road automobiles. This research introduced a validated computational fluid dynamics (CFD) model regarding this concern. Such an aerodynamic impact mechanism was explored; a relationship between the transverse distance between train and motor-van (hereinfafter referred to as van) and the aerodynamic effects on the van was explored to help the optimization of bridge decks, and the relationship between the automobile speed and aerodynamic variations of a van was fitted to help traffic control. The fitting results are accurate enough for further research. It is noted that the relative speed of the two automobiles is not the only factor that influences the aerodynamic variations of the van, even at a confirmed relative velocity, the aerodynamic variations of the van vary a lot as the velocity proportion changes, and the most unfavorable case shows an increase of over 40% on the aerodynamic variations compared to the standard case. The decay of the aerodynamic effects shows that not all the velocity terms would enhance the aerodynamic variations; the coupled velocity term constrains the variation amplitude of moments and decreases the total amplitude by 20%–40%.

The compressive strength of self-compacting concrete (SCC) needs to be determined during the construction design process. This paper shows that the compressive strength of SCC (CS of SCC) can be successfully predicted from mix design and curing age by a machine learning (ML) technique named the Extreme Gradient Boosting (XGB) algorithm, including non-hybrid and hybrid models. Nine ML techniques, such as Linear regression (LR), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Trees (DTR), Random Forest (RF), Gradient Boosting (GB), and Artificial Neural Network using two training algorithms LBFGS and SGD (denoted as ANN_LBFGS and ANN_SGD), are also compared with the XGB model. Moreover, the hybrid models of eight ML techniques and Particle Swarm Optimization (PSO) are constructed to highlight the reliability and accuracy of SCC compressive strength prediction by the XGB_PSO hybrid model. The highest number of SCC samples available in the literature is collected for building the ML techniques. Compared with previously published works’ performance, the proposed XGB method, both hybrid and non-hybrid models, is the most reliable and robust of the examined techniques, and is more accurate than existing ML methods (R² = 0.9644, RMSE = 4.7801, and MAE = 3.4832). Therefore, the XGB model can be used as a practical tool for engineers in predicting the CS of SCC.