Today, the most commonly used civil infrastructure inspection method is based on a visual assessment conducted by certified inspectors following prescribed protocols. However, the increase in aggressive environmental and load conditions, coupled with the achievement of many structures of the life-cycle end, has highlighted the need to automate damage identification and satisfy the number of structures that need to be inspected. To overcome this challenge, this paper presents a method for automating concrete damage classification using a deep convolutional neural network. The convolutional neural network was designed after an experimental investigation of a wide number of pretrained networks, applying the transfer-learning technique. Training and validation were conducted using a database built with 1352 images balanced between “undamaged”, “cracked”, and “delaminated” concrete surfaces. To increase the network robustness compared to images in real-world situations, different image configurations have been collected from the Internet and on-field bridge inspections. The GoogLeNet model, with the highest validation accuracy of approximately 94%, was selected as the most suitable network for concrete damage classification. The results confirm that the proposed model can correctly classify images from real concrete surfaces of bridges, tunnels, and pavement, resulting in an effective alternative to the current visual inspection techniques.
The aim of this study is to propose a new detection method for determining the damage locations in pile foundations based on deep learning using acoustic emission data. First, the damage location is simulated using a back propagation neural network deep learning model with an acoustic emission data set acquired from pile hit experiments. In particular, the damage location is identified using two parameters: the pile location (PL) and the distance from the pile cap (DS). This study investigates the influences of various acoustic emission parameters, numbers of sensors, sensor installation locations, and the time difference on the prediction accuracy of PL and DS. In addition, correlations between the damage location and acoustic emission parameters are investigated. Second, the damage step condition is determined using a classification model with an acoustic emission data set acquired from uniaxial compressive strength experiments. Finally, a new damage detection and evaluation method for pile foundations is proposed. This new method is capable of continuously detecting and evaluating the damage of pile foundations in service.
Facial support in slurry shield tunneling is provided by slurry pressure to balance the external earth and water pressure. Hydraulic fracturing may occur and cause a significant decrease in the support pressure if the slurry pressure exceeds the threshold of the soil or rock material, resulting in a serious face collapse accident. Preventing the occurrence of hydraulic fracturing in a slurry shield requires investigating the effects of related influencing factors on the hydraulic fracturing pressure and fracture pattern. In this study, a hydraulic fracturing apparatus was developed to test the slurry-induced fracturing of cohesive soil. The effects of different sample parameters and loading conditions, including types of holes, unconfined compressive strength, slurry viscosity, and axial and circumferential loads, on the fracturing pressure and fracture dip were examined. The results indicate that the fracture dip is mainly affected by the deviator stress. The fracturing pressure increases linearly with the increase in the circumferential pressure, but it is almost independent of the axial pressure. The unconfined compressive strength of soil can reflect its ability to resist fracturing failure. The fracturing pressure increases with an increase in the unconfined compressive strength as well as the slurry viscosity. Based on the test results, an empirical approach was proposed to estimate the fracturing pressure of the soil.
Seismic modeling of massive structures requires special caution, as wave propagation effects significantly affect the responses. This becomes more crucial when the path-dependent behavior of the material is considered. The coexistence of these conditions renders numerical earthquake analysis of concrete dams challenging. Herein, a finite element model for a comprehensive nonlinear seismic simulation of concrete gravity dams, including realistic soil–structure interactions, is introduced. A semi-infinite medium is formulated based on the domain reduction method in conjunction with standard viscous boundaries. Accurate representation of radiation damping in a half-space medium and wave propagation effects in a massed foundation are verified using an analytical solution of vertically propagating shear waves in a viscoelastic half-space domain. A rigorous nonlinear finite element model requires a precise description of the material response. Hence, a microplane-based anisotropic damage–plastic model of concrete is formulated to reproduce irreversible deformations and tensorial degeneration of concrete in a coupled and rate-dependent manner. Finally, the Koyna concrete gravity dam is analyzed based on different assumptions of foundation, concrete response, and reservoir conditions. Comparison between responses obtained based on conventional assumptions with the results of the presented comprehensive model indicates the significance of considering radiation damping and employing a rigorous constitutive material model, which is pursued for the presented model.
In this study, a fully precast steel–ultrahigh performance concrete (UHPC) lightweight composite bridge (LWCB) was proposed based on Mapu Bridge, aiming at accelerating construction in bridge engineering. Cast-in-place joints are generally the controlling factor of segmental structures. Therefore, an innovative girder-to-girder joint that is suitable for LWCB was developed. A specimen consisting of two prefabricated steel–UHPC composite girder parts and one post-cast joint part was fabricated to determine if the joint can effectively transfer load between girders. The flexural behavior of the specimen under a negative bending moment was explored. Finite element analyses of Mapu Bridge showed that the nominal stress of critical sections could meet the required stress, indicating that the design is reasonable. The fatigue performance of the UHPC deck was assessed based on past research, and results revealed that the fatigue performance could meet the design requirements. Based on the test results, a crack width prediction method for the joint interface, a simplified calculation method for the design moment, and a deflection calculation method for the steel–UHPC composite girder in consideration of the UHPC tensile stiffness effect were presented. Good agreements were achieved between the predicted values and test results.
In this study, we conducted experimental tests on two specimens of reinforced concrete beams using a three-point bending test to optimize the flexure and stiffness designs. The first specimen is a reinforced concrete beam with an ordinary reinforcement, and the second specimen has an invented reinforcement system that consists of an ordinary reinforcement in addition to three additional bracings using steel bars and steel plates. The results of the flexure test were collected and analyzed, and the flexural strength, the rate of damage during bending, and the stiffness were determined. Finite element modeling was applied for both specimens using the LS-DYNA program, and the simulation results of the flexure test for the same outputs were determined. The results of the experimental tests showed that the flexural strength of the invented reinforcement system was significantly enhanced by 15.5% compared to the ordinary system. Moreover, the flexural cracks decreased to a significant extent, manifesting extremely small and narrow cracks in the flexure spread along the bottom face of the concrete. In addition, the maximum deflection for the invented reinforced concrete beam decreased to 1/3 compared to that of an ordinary reinforced concrete beam. The results were verified through numerical simulations, which demonstrated excellent similarities between the flexural failure and the stiffness of the beam. The invented reinforcement system exhibited a high capability in boosting the flexure design and stiffness.
Beam–column connections are one of the most critical elements of reinforced concrete structures, especially in seismically active regions, and have been extensively evaluated experimentally and numerically. However, very limited experimental studies about eccentric reinforced concrete connections including the effect of connected slabs are available. This study presents the experimental results of two half-scale eccentric beam-column-slab connections subjected to quasi-static cyclic loading. The horizontal eccentricity (eh) is maintained at 12.5% and 25% of column width (bc) for specimens 1 and 2, respectively. The damage pattern, performance levels, displacement ductility (μD), energy dissipation, and connection strength and stiffness are compared for both specimens, and the effect of eccentricity is evaluated. It is concluded that the eccentricity has no significant effect on the lateral load carrying capacity; however, the overall strength degradation increases with the increase in eccentricity. Similarly, the elastic stiffness of specimen 2 decreased by 14% as the eccentricity increased from 12.5% to 25%; however, the eccentricity had no significant effect on the overall stiffness degradation. μD decreased by 43%, and the energy dissipation capacity decreased by 40% in specimen 2 with higher eccentricity. The story drifts corresponding to the performance levels of the life safety (LS) and collapse prevention (CP) were found to be 28% lesser in specimen 2 than in specimen 1.
Twelve ECC beams with three different fiber types, along with four normal concrete beams, were tested in this study to evaluate the influence of cross-sectional hollowing on their flexural performance. The fiber types used were nylon monofilament (NM), low-cost untreated polyvinyl alcohol (PVA), and polypropylene (PP). Three different square hole sizes of 60, 80, and 100 mm with cross-sectional hollowing ratios of 0.16, 0.28, and 0.44, respectively, were adopted for each group of beams in addition to a solid beam. All beams were tested under four-point loading using a displacement-controlled testing machine. The test results showed that ECC beams can mostly withstand higher cracking and ultimate loads compared to their corresponding normal concrete versions. The results also showed that both the ductility and toughness of the ECC beams are higher than those of the normal concrete beams and that the ductility values of the hollow beams with a hole size of 60 mm are higher than those of the corresponding solid beams. Moreover, hollow ECC beams with hole sizes of 60 and 80 mm exhibited a higher ductility than a solid normal concrete beam.
The creation of the new “Ferry-Free Coastal Highway Route E39” in southwest Norway entails the production of a remarkable quantity of crushed rocks. These resources could be beneficially employed as aggregates in the unbound courses of the highway itself or other road pavements present nearby. Two innovative stabilizing agents, organosilane and lignosulfonate, can significantly enhance the key properties, namely, resilient modulus and resistance against permanent deformation, of the aggregates that are excessively weak in their natural state. The beneficial effect offered by the additives was thoroughly evaluated by performing repeated load triaxial tests. The study adopted the most common numerical models to describe these two key mechanical properties. The increase in the resilient modulus and reduction in the accumulated vertical permanent deformation show the beneficial impact of the additives. Furthermore, a finite element model was created to simulate the repeated load triaxial test by implementing nonlinear elastic and plastic constitutive relationships.
In the present study, the effect of material microstructure on the mechanical response of a two-dimensional elastic layer perfectly bonded to a substrate is examined under surface loadings. In the current model, the substrate is treated as an elastic half plane as opposed to a rigid base, and this enables its applications in practical cases when the modulus of the layer (e.g., the coating material) and substrate (e.g., the coated surface) are comparable. The material microstructure is modeled using the generalized continuum theory of couple stress elasticity. The boundary value problems are formulated in terms of the displacement field and solved in an analytical manner via the Fourier transform and stiffness matrix method. The results demonstrate the capability of the present continuum theory to efficiently model the size-dependency of the response of the material when the external and internal length scales are comparable. Furthermore, the results indicated that the material mismatch and substrate stiffness play a crucial role in the predicted elastic field. Specifically, the study also addresses significant discrepancy of the response for the case of a layer resting on a rigid substrate.
The implementation of novel machine learning models can contribute remarkably to simulating the degradation of concrete due to environmental factors. This study considers the sulfuric acid corrosive factor in wastewater systems to simulate concrete mass loss using five machine learning models. The models include three different types of extreme learning machines, including the standard, online sequential, and kernel extreme learning machines, in addition to the artificial neural network, classification and regression tree model, and statistical multiple linear regression model. The reported values of concrete mass loss for six different types of concrete are the target values of the machine learning models. The input variability was assessed based on two scenarios prior to the application of the predictive models. For the first assessment, the machine learning models were developed using all the available cement and concrete mixture input variables; the second assessment was conducted based on the gamma test approach, which is a sensitivity analysis technique. Subsequently, the sensitivity analysis of the most effective parameters for concrete corrosion was tested using three different approaches. The adopted methodology attained optimistic and reliable modeling results. The online sequential extreme learning machine model demonstrated superior performance over the other investigated models in predicting the concrete mass loss of different types of concrete.
Many uncertain factors in the excavation process may lead to excessive lateral displacement or over-limited internal force of the piles, as well as inordinate settlement of soil surrounding the existing bridge foundation. Safety control is pivotal to ensuring the safety of adjacent structures. In this paper, an innovative method is proposed that combines an analytic hierarchy process (AHP) with a finite element method (FEM) to reveal the potential impact risk of uncertain factors on the surrounding environment. The AHP was adopted to determine key influencing factors based on the weight of each influencing factor. The FEM was used to quantify the impact of the key influencing factors on the surrounding environment. In terms of the AHP, the index system of uncertain factors was established based on an engineering investigation. A matrix comparing the lower index layer to the upper index layer, and the weight of each influencing factor, were calculated. It was found that the excavation depth and the distance between the foundation pit and the bridge foundation were fundamental factors. For the FEM, the FE baseline model was calibrated based on the case of no bridge surrounding the foundation pit. The consistency between the monitoring data and the numerical simulation data for a ground settlement was analyzed. FE simulations were then conducted to quantitatively analyze the degree of influence of the key influencing factors on the bridge foundation. Furthermore, the lateral displacement of the bridge pile foundation, the internal force of the piles, and the settlement of the soil surrounding the pile foundation were emphatically analyzed. The most hazardous construction condition was also determined. Finally, two safety control measures for increasing the numbers of support levels and the rooted depths of the enclosure structure were suggested. A novel method for combining AHP with FEM can be used to determine the key influencing aspects among many uncertain factors during a construction, which can provide some beneficial references for engineering design and construction.
The aim of this study is to investigate the applicability of reliability theory on surface square/rectangular footing against bearing capacity failure using fuzzy set theory in conjunction with the finite element method. Soil is modeled as a three-dimensional spatially varying medium, where its parameters (cohesion, friction angle, unit weight, etc.) are considered as fuzzy variables that maintain some membership functions. Soil is idealized as an elastic-perfectly plastic material obeying the Mohr–Coulomb failure criterion, where both associated and non-associated flow rules are considered in estimating the ultimate bearing capacity of the footing. The spatial variability of the soil is incorporated for both isotropic and anisotropic fields, which are determined by the values of scales of fluctuation in both the horizontal and vertical directions. A new parameter namely, limiting applied pressure at zero failure probability is proposed, and it indirectly predicts the failure probability of the footing. The effect of the coefficient of variation of the friction angle of the soil on the probability of failure is analyzed, and it is observed that the effect is significant. Furthermore, the effect of the scale of fluctuation on the probability of failure is investigated, and the necessity for considering spatial variability in the reliability analysis is well proven.
This study investigates the performance of four machine learning (ML) algorithms to evaluate the earthquake-induced liquefaction potential of soil based on the cone penetration test field case history records using the Bayesian belief network (BBN) learning software Netica. The BBN structures that were developed by ML algorithms-K2, hill climbing (HC), tree augmented naive (TAN) Bayes, and Tabu search were adopted to perform parameter learning in Netica, thereby fixing the BBN models. The performance measure indexes, namely, overall accuracy (OA), precision, recall, F-measure, and area under the receiver operating characteristic curve, were used to evaluate the training and testing BBN models’ performance and highlight the capability of the K2 and TAN Bayes models over the Tabu search and HC models. The sensitivity analysis results showed that the cone tip resistance and vertical effective stress are the most sensitive factors, whereas the mean grain size is the least sensitive factor in the prediction of seismic soil liquefaction potential. The results of this study can provide theoretical support for researchers in selecting appropriate ML algorithms and improving the predictive performance of seismic soil liquefaction potential models.
Lateral displacement due to liquefaction (DH) is the most destructive effect of earthquakes in saturated loose or semi-loose sandy soil. Among all earthquake parameters, the standardized cumulative absolute velocity (CAV5) exhibits the largest correlation with increasing pore water pressure and liquefaction. Furthermore, the complex effect of fine content (FC) at different values has been studied and demonstrated. Nevertheless, these two contexts have not been entered into empirical and semi-empirical models to predict DH. This study bridges this gap by adding CAV5 to the data set and developing two artificial neural network (ANN) models. The first model is based on the entire range of the parameters, whereas the second model is based on the samples with FC values that are less than the 28% critical value. The results demonstrate the higher accuracy of the second model that is developed even with less data. Additionally, according to the uncertainties in the geotechnical and earthquake parameters, sensitivity analysis was performed via Monte Carlo simulation (MCS) using the second developed ANN model that exhibited higher accuracy. The results demonstrated the significant influence of the uncertainties of earthquake parameters on predicting DH.
This study aims to improve the unconfined compressive strength of soils using additives as well as by predicting the strength behavior of stabilized soils using two artificial-intelligence-based models. The soils used in this study are stabilized using various combinations of cement, lime, and rice husk ash. To predict the results of unconfined compressive strength tests conducted on soils, a comprehensive laboratory dataset comprising 137 soil specimens treated with different combinations of cement, lime, and rice husk ash is used. Two artificial-intelligence-based models including artificial neural networks and support vector machines are used comparatively to predict the strength characteristics of soils treated with cement, lime, and rice husk ash under different conditions. The suggested models predicted the unconfined compressive strength of soils accurately and can be introduced as reliable predictive models in geotechnical engineering. This study demonstrates the better performance of support vector machines in predicting the strength of the investigated soils compared with artificial neural networks. The type of kernel function used in support vector machine models contributed positively to the performance of the proposed models. Moreover, based on sensitivity analysis results, it is discovered that cement and lime contents impose more prominent effects on the unconfined compressive strength values of the investigated soils compared with the other parameters.
Ensuring a safe foundation design in soft clay is always a challenging task to engineers. In the present study, the effectiveness of under-reamed piles in soft clay underlaid by stiff clay is numerically studied using the lower-bound finite element limit analysis (LB FELA). The bearing and uplift capacities of under-reamed piles are estimated through non-dimensional factors Ncul and Fcul, respectively. These factors increased remarkably and marginally compared to Ncul and Fcul of the piles without bulbs when the bulb is placed in stiff and soft clay, respectively. For a given ratio of undrained cohesion of stiff to soft clay (c2/c1), the factors Ncul and Fcul moderately increased with the increase in the length-to-shaft-diameter ratio (Lu/D) and adhesion factors in soft clay (αs1) and stiff clay (αs2). The variation of radial stress along the pile–soil interface, distribution of axial force in the under-reamed piles, and state of plastic shear failure in the soil are also studied under axial compression and tension. The results of this study are expected to be useful for the estimation of the bearing and uplift capacities of under-reamed piles in uniform clay and soft clay underlaid by stiff clay.
Considering failures during machinery processes such as drilling, a precautionary analysis involving delamination and the corresponding dissipated energy is required, especially for composite structures. In this context, because of the complexity of both the analysis procedure and experimental test setup, most studies prefer to represent mode I and III interlaminar crack propagation instead of that involving mode II. Therefore, in this study, the effect of mode II delamination and corresponding interlaminar crack propagation was considered during the drilling process of multilayered glass/polyester composites using both numerical and experimental approaches. In the experimental procedure, the mechanical properties of the glass/polyester specimens were obtained according to ASTM D3039. In addition, the interlaminar mixed-mode (I/II) loadings were determined using an ARCAN test fixture so that the fracture toughness of glass/polyester could then be identified. The mode II critical strain energy release rate (CSERR) was then obtained using an experimental test performed using an ARCAN fixture and the virtual crack closure technique (VCCT). It was determined that the numerical approach was in accordance with the experiments, and more than 95% of crack propagation could be attributed to mode II compared to the two other modes.