Search results

Cracks are prevalent signs of pavement distress found on highways globally. The use of artificial intelligence (AI) and deep learning (DL) for crack detection is increasingly considered as an optimal solution. Consequently, this paper introduces a novel, fully connected, optimised convolutional neural network (CNN) model using feature selection algorithms for the purpose of detecting cracks in highway pavements.

To enhance the accuracy of the CNN model for crack detection, the authors employed a fully connected deep learning layers CNN model along with several optimisation techniques. Specifically, three optimisation algorithms, namely adaptive moment estimation (ADAM), stochastic gradient descent with momentum (SGDM), and RMSProp, were utilised to fine-tune the CNN model and enhance its overall performance. Subsequently, the authors implemented eight feature selection algorithms to further improve the accuracy of the optimised CNN model. These feature selection techniques were thoughtfully selected and systematically applied to identify the most relevant features contributing to crack detection in the given dataset. Finally, the authors subjected the proposed model to testing against seven pre-trained models.

The study's results show that the accuracy of the three optimisers (ADAM, SGDM, and RMSProp) with the five deep learning layers model is 97.4%, 98.2%, and 96.09%, respectively. Following this, eight feature selection algorithms were applied to the five deep learning layers to enhance accuracy, with particle swarm optimisation (PSO) achieving the highest F-score at 98.72. The model was then compared with other pre-trained models and exhibited the highest performance.

With an achieved precision of 98.19% and F-score of 98.72% using PSO, the developed model is highly accurate and effective in detecting and evaluating the condition of cracks in pavements. As a result, the model has the potential to significantly reduce the effort required for crack detection and evaluation.

The proposed method for enhancing CNN model accuracy in crack detection stands out for its unique combination of optimisation algorithms (ADAM, SGDM, and RMSProp) with systematic application of multiple feature selection techniques to identify relevant crack detection features and comparing results with existing pre-trained models.

This review paper seeks to enhance knowledge of how pre-loading affects reinforced concrete (RC) beams under fire. It investigates key factors like deflection and load capacity to understand pre-loading's role in replicating RC beams' actual responses to fire, aiming to improve fire testing protocols and structural fire engineering design.

This review systematically aggregates data from existing literature on the fire response of RC beams, comparing scenarios with (WP) and without pre-loading (WOP). Through statistical tools like the two-tailed t-test and Mann–Whitney U-test, it assesses deflection extremes. The study further examines structural responses, including flexural and shear behavior, ultimate load capacity, post-yield behavior, stiffness degradation and failure modes. The approach concludes with a statistical forecast of ideal pre-load levels to elevate experimental precision and enhance fire safety standards.

The review concludes that pre-loading profoundly affects the fire response of RC beams, suggesting a 35%–65% structural capacity range for realistic simulations. The review also recommended the initial crack load as an alternative metric for determining the pre-loading impact. Crucially, it highlights that pre-loading not only influences the fire response but also significantly alters the overall structural behavior of the RC beams.

The review advances structural fire engineering with an in-depth analysis of pre-loading's impact on RC beams during fire exposure, establishing a validated pre-load range through thorough statistical analysis and examination of previous research. It refines experimental methodologies and structural design accuracy, ultimately bolstering fire safety protocols.

The purpose of this study is to use the corrected stress field theory to derive the shear capacity of geopolymer concrete beams (GPC) and consider the shear-span ratio as a major factor affecting the shear capacity. This research aims to provide guidance for studying the shear capacity of GPC and to observe how the failure modes of beams change with the variation of the shear-span ratio, thereby discovering underlying patterns.

Three test beams with shear span ratios of 1.5, 2.0 and 2.5 are investigated in this paper. For GPC beams with shear-span ratios of 1.5, 2.0 and 2.5, ultimate capacities are 337kN, 235kN and 195kN, respectively. Transitioning from 1.5 to 2.0 results in a 30% decrease in capacity, a reduction of 102kN. Moving from 2.0 to 2.5 sees a 17% decrease, with a loss of 40KN in capacity. A shear capacity formula, derived from modified compression field theory and considering concrete shear strength, stirrups and aggregate interlocking force, was validated through finite element modeling. Additionally, models with shear ratios of 1 and 3 were created to observe crack propagation patterns.

For GPC beams with shear-span ratios of 1.5, 2.0 and 2.5, ultimate capacities of 337KN, 235KN and 195KN are achieved, respectively. A reduction in capacity of 102KN occurs when transitioning from 1.5 to 2.0 and a decrease of 40KN is observed when moving from 2.0 to 2.5. The average test-to-theory ratio, at 1.015 with a variance of 0.001, demonstrates strong agreement. ABAQUS models beams with ratios ranging from 1.0 to 3.0, revealing crack trends indicative of reduced crack angles with higher ratios. The failure mode observed in the models aligns with experimental results.

This article provides a reference for the shear bearing capacity formula of geopolymer reinforced concrete (GRC) beams, addressing the limited research in this area. Additionally, an exponential model incorporating the shear-span ratio as a variable was employed to calculate the shear capacity, based on previous studies. Moreover, the analysis of shear capacity results integrated literature from prior research. By fitting previous experimental data to the proposed formula, the accuracy of this study's derived formula was further validated, with theoretical values aligning well with experimental results. Additionally, guidance is offered for utilizing ABAQUS in simulating the failure process of GRC beams.

The use of waste polyethylene terephthalate (PET) plastics derived from shredded bottles in concrete is not formalized yet, especially in reinforced members such as beams and columns. The disposal of plastic wastes in concrete is a viable alternative to manage those wastes while minimizing the environmental impacts associated to recycling, carbon dioxide emissions and energy consumption.

This paper evaluates the suitability of 2D deterministic and stochastic finite element (FE) modeling to predict the shear strength behavior of reinforced concrete (RC) beams without stirrups. Different concrete mixtures prepared with 1.5%–4.5% PET additions, by volume, are investigated.

Test results showed that the deterministic and stochastic FE approaches are accurate to assess the maximum load of RC beams at failure and corresponding midspan deflection. However, the crack patterns observed experimentally during the different stages of loading can only be reproduced using the stochastic FE approach. This later method accounts for the concrete heterogeneity due to PET additions, allowing a statistical simulation of the effect of mechanical properties (i.e. compressive strength, tensile strength and Young’s modulus) on the output FE parameters.

Data presented in this paper can be of interest to civil and structural engineers, aiming to predict the failure mechanisms of RC beams containing plastic wastes, while minimizing the experimental time and resources needed to estimate the variability effect of concrete properties on the performance of such structures.

Passive chipless RFID (radio frequency identification) sensors, devoid of batteries or wires for data transmission to a signal reader, demonstrate stability in severe conditions. Consequently, employing these sensors for metal crack detection ensures ease of deployment, longevity and reusability. This study aims to introduce a chipless RFID sensor design tailored for detecting metal cracks, emphasizing tag reusability and prolonged service life.

The passive RFID sensor is affixed to the surface of the aluminum plate under examination, positioned over the metal cracks. These cracks alter the electrical length of the sensor, thereby influencing its amplitude-frequency characteristics. Hence, the amplitude-frequency profile generated by various metal cracks can effectively ascertain the occurrence and orientation of the cracks.

Simulation and experimental results show that the proposed crack sensing tag produces different frequency amplitude changes for four directions of cracks and can recognize the crack direction. The sensor has a small size and simple structure, which makes it easy to deploy.

This research aims to deploy crack detection on metallic surfaces using passive chipless RFID sensors, analyze the amplitude-frequency characteristics of crack formation and distinguish cracks of varying widths and orientations. The designed sensor boasts a straightforward structural design, facilitating ease of deployment, and offers a degree of reusability.

Recently, the repairing of reinforced concrete (RC) structures attracted great research attentions, but the research interests were mainly concentrated on common repairing types. To this end, in this paper, a repairing of pre-loaded RC beams strengthened by aramid reinforcement polymers (AFRP) is presented. Furthermore, the purpose of this paper is to study the behavior of pre-loaded RC Deep beams under sustained load. The AFRP has many advantages such as controlling stresses distribution around the openings, controlling failure modes, and enhancing the structural capacity of pre-cracked RC beams.

Four specimens were experimentally tested: one specimen without strengthening, which is considered as control specimen, one strengthened specimen using AFRP without pre-cracking and two specimens subjected to pre-cracking load before prior to AFRP application. Furthermore, after validation of experimental data by using ANSYS software, a parametric study was conducted to investigate the effect of pre-damage level on shear capacity of RC beams. For pre-cracked beams, loading was first applied until the cracking stage, followed by specimen repairing with epoxy injection, and then the specimens were loaded again until failure point.

The result showed that pre-damage level and AFRP strengthening have great influence on the ultimate strength and failure mode. In addition, the results obtained from experimental tests were compared with those from numerical validation with ANSYS and showed good agreement.

Based on ACI guidelines, an analytical equation for calculating the shear strength of strengthened RC beams with openings subjected to pre-damage was then proposed, and the calculated results were compared with those from the tests, with differences not exceeding 10%.

The application of reinforcing old bridges by adding external prestressed steel bundles is becoming more and more widespread. However, the long-term safety performance test of the strengthening method is rarely carried out. In this paper, the bearing capacity of a 420 m prestressed concrete (PC) continuous girder bridge after five years of strengthening is analyzed.

The bridge model of the bridge structure and strengthening scheme is established by the finite element software of the bridge. The theoretical load-bearing capacity of the bridge under the latest standard load grade is obtained by finite element analysis. The actual bearing capacity of the bridge is obtained by field test. Through the comparative analysis of theory and practice, the health state of the bridge after five years of reinforced operation is judged. The damage to the overall stiffness and external prestressing of the bridge is also analyzed.

The results of deflection and strain show that the stiffness and strength of the secondary side span and the middle span decrease slightly, and the maximum reduction of bearing capacity is 4.5%. The static stiffness of the whole bridge decreases as a result of cracks, and the maximum decrease is 21%. In the past five years, the relaxation loss of the external prestressing of the bridge is 3.31–3.97%, which is the main reason for the decrease in bearing capacity.

Through the joint analysis of the bridge stiffness and the loss of external prestressing, the strengthening condition of the bridge after five years of operation is effectively analyzed. The strengthening effect of the external prestressed steel beam strengthening method is analyzed, which can provide a reference for similar bridge strengthening.

To understand the seismic behavior of reinforced concrete (RC) beams confined by corroded stirrups, low-reversed cyclic loading tests were carried out on seven RC beam specimens with different stirrup corrosion levels and stirrup ratios to investigate their mechanical characteristics.

The failure mode, hysteresis behavior, skeleton curves, ductility, stiffness degradation and energy dissipation behavior of RC specimens are compared and discussed. The experimental results showed that the restraint of concrete provided by corroded stirrups is reduced, which leads to a decline in seismic performance.

For the specimens with the same ratios of stirrup, as the corrosion level increased, the load-carrying capacity, stiffness, plastic deformation capacity and energy-dissipation capacity dropped significantly. Compared with the uncorroded specimen, the failure modes of specimens with high corrosion level changed from ductile bending failure to brittle failure. For the specimens with the same levels of corrosion, the higher the stirrup ratio was, the stronger the restraint effect of the stirrups on the concrete, and the seismic behavior of the specimens was obviously improved.

In this paper, a total of seven full-size RC beam specimens at joints with different stirrup corrosion levels and stirrup ratios were designed and constructed to explore the influences of corrosion levels and stirrup ratios of stirrups on the seismic performances. The failure modes, strain of reinforcement, hysteretic curves, skeleton curves, stiffness degradation and ductility factor of RC specimens are compared and discussed.

The paper aims to introduces an experimental work to investigate the torsional behavior of reinforced concrete (RC) beams strengthened by near-surface mounted (NSM) carbon fiber-reinforced polymer (CFRP) ropes.

In this research, nine rectangular RC beams of 250 mm × 300 mm cross-section and 1,600 mm in length were constructed and tested considering the studied parameters. These parameters include the length of the CFRP rope, the orientation of the CFRP rope, the arrangement of longitudinal and the scheme of NSM-CFRP ropes.

In comparison to control specimens, the results demonstrate a considerable improvement in the torsional response of RC beams strengthened with the CFRP rope. Additionally, specimens strengthened with 90° vertical ropes increase torsional moment capacity more efficiently than specimens strengthened with 45° inclined ropes since the stress concentration leads to premature debonding of the CFRP rope. Whereas RC beams' ability to withstand torsional moments is reduced as the distance between reinforcing CFRP ropes is increased. According to test results, adding CFRP ropes to RC beams' bottoms had a slightly positive impact on torsional response.

This paper fulfills an identified need to study how the using of the CFRP rope is effective in strengthening RC beam subjected to torsion moment.

Low-carbon concrete represents a new direction in mitigating the global warming effects caused by clinker manufacturing. Utilizing Saudi agro-industrial by-products as an alternative to cement is a key support in reducing clinker production and promoting innovation in infrastructure and circular economy concepts, toward decarbonization in the construction industry. The use of fly ash (FA) as a cement alternative has been researched and proven effective in enhancing the durability of FA-based concrete, especially at lower replacement levels. However, at higher replacement levels, a noticeable impediment in mechanical strength indicators limits the use of this material.

In this study, low-carbon concrete mixes were designed by replacing 50% of the cement with FA. Varying ratios of nano-sized glass powder (4 and 6% of cement weight) were used as nanomaterial additives to enhance the mechanical properties and durability of the designed concrete. In addition, a 10% of the mixing water was replaced with EMs dosage.

The results obtained showed a significant positive impact on resistance and durability properties when replacing 10% of the mixing water with effective microorganisms (EMs) broth and incorporating nanomaterial additives. The optimal mix ratios were those designed with 10% EMs and 4–6% nano-sized glass powder additives. However, it can be concluded that advancements in eco-friendly concrete additive technologies have made significant contributions to the development of sophisticated concrete varieties.

This study focused at developing nanomaterial additives from Saudi industrial wastes and at presenting a cost-effective and feasible solution for enhancing the properties of FA-based concrete. It has also been found that the inclusion of EMs contributes effectively to enhancing the concrete's resistance properties.