• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.77-91
• /
• 2022

Various monitoring systems have been implemented in civil infrastructure to ensure structural safety and integrity. In long-term monitoring, these systems generate a large amount of data, where anomalies are not unusual and can pose unique challenges for structural health monitoring applications, such as system identification and damage detection. Therefore, developing efficient techniques is quite essential to recognize the anomalies in monitoring data. In this study, several machine learning techniques are explored and implemented to detect and classify various types of data anomalies. A field dataset, which consists of one month long acceleration data obtained from a long-span cable-stayed bridge in China, is employed to examine the machine learning techniques for automated data anomaly detection. These techniques include the statistic-based pattern recognition network, spectrogram-based convolutional neural network, image-based time history convolutional neural network, image-based time-frequency hybrid convolution neural network (GoogLeNet), and proposed ensemble neural network model. The ensemble model deliberately combines different machine learning models to enhance anomaly classification performance. The results show that all these techniques can successfully detect and classify six types of data anomalies (i.e., missing, minor, outlier, square, trend, drift). Moreover, both image-based time history convolutional neural network and GoogLeNet are further investigated for the capability of autonomous online anomaly classification and found to effectively classify anomalies with decent performance. As seen in comparison with accuracy, the proposed ensemble neural network model outperforms the other three machine learning techniques. This study also evaluates the proposed ensemble neural network model to a blind test dataset. As found in the results, this ensemble model is effective for data anomaly detection and applicable for the signal characteristics changing over time.

• Geomechanics and Engineering
• /
• v.31 no.6
• /
• pp.599-614
• /
• 2022

One of the methods of stabilizing retaining walls, embankments, and deep excavations is the implementation of plate anchors (like the Geolock wall anchor systems). Back-to-back Mechanically Stabilized Earth (BBMSE) walls are common stabilized earth structures that can be used for bridge ramps. But so far, the analysis of the interactive behavior of two back-to-back anchored walls (BBAW) by double-plates anchors (constructed closely from each other and subjected to the limited-breadth vertical loading) including interference of their failure and sliding surfaces has not been the subject of comprehensive studies. Indeed, in this compound system, the interaction of sliding wedges of these two back-to-back walls considering the shear failure wedge of the foundation, significantly impresses on the foundation bearing capacity, adjacent walls displacements and deformations, and their stability. In this study, the effect of horizontal distance between two walls (W), breadth of loading plate (B), and position of vertical loading was investigated experimentally. In addition, the comparison of using single and equivalent double-plate anchors was evaluated. The loading plate bearing capacity and displacements, and deformations of BBAW were measured and the results are presented. To evaluate the shape, form, and how the critical failure surfaces of the soil behind the walls and beneath the foundation intersect with one another, the Particle Image Velocimetry (PIV) technique was applied. The experimental tests results showed that in this composite system (two adjacent-loaded BBAW) the effective distance of walls is about W = 2.5*H (H: height of walls) and the foundation effective breadth is about B = H, concerning foundation bearing capacity, walls horizontal displacements and their deformations. For more amounts of W and B, the foundation and walls can be designed and analyzed individually. Besides, in this compound system, the foundation bearing capacity is an exponential function of the System Geometry Variable (SGV) whereas walls displacements are a quadratic function of it. Finally, as an important achievement, doubling the plates of anchors can facilitate using concrete walls, which have limitations in tolerating curvature.

• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.393-407
• /
• 2023

To assess structural condition in a non-destructive manner, computer vision-based structural health monitoring (SHM) has become a focus. Compared to traditional contact-type sensors, the advantages of computer vision-based measurement systems include lower installation costs and broader measurement areas. In this study, we propose a novel computer vision-based vibration measurement and coarse-to-fine damage assessment method for truss bridges. First, a deep learning model FairMOT is introduced to track the regions of interest (ROIs) that include joints to enhance the automation performance compared with traditional target tracking algorithms. To calculate the displacement of the tracked ROIs accurately, a normalized cross-correlation method is adopted to fine-tune the offset, while the Harris corner matching is utilized to correct the vibration displacement errors caused by the non-parallel between the truss plane and the image plane. Then, based on the advantages of the stochastic damage locating vector (SDLV) and Bayesian inference-based stochastic model updating (BI-SMU), they are combined to achieve the coarse-to-fine localization of the truss bridge's damaged elements. Finally, the severity quantification of the damaged components is performed by the BI-SMU. The experiment results show that the proposed method can accurately recognize the vibration displacement and evaluate the structural damage.

• Journal of the Korean Geotechnical Society
• /
• v.22 no.10
• /
• pp.121-129
• /
• 2006

Stone column is one of the ground improvement systems which is being used for accelerating consolidation and increasing bearing capacity for settlement sensitive structures like load embankments, bridge abutments, oil storage tanks etc. The effects of this method are enhancement of ground bearing capacity, reduction of settlement, prevention of liquefaction and prevention of lateral ground movement. Recently, geosynthetic reinforced (encased) stone column approach has been developed to improve its load carrying capacity through increasing confinement effect. Although such a concept has successfully been applied in practice, fundamentals of the method have not been fully explored. This paper presents the results of an investigation on the bearing capacity and failure mechanism of geogrid-encased stone column by model tests. The results of the analyses indicated improved bearing capacity of the geogrid reinforced stone column method over the conventional strone column method with no encasing.

• Journal of the Korean Geotechnical Society
• /
• v.23 no.7
• /
• pp.99-104
• /
• 2007

The deep soil mixing, on ground modification technique, has been used for many diverse applications including building and bridge foundations, port and harbor foundations, retaining structures, liquefaction mitigation, temporary support of excavation and water control. This method has the basic objective of finding the most efficient and economical method for mixing cement with soil to secure settlements through improvement of stability on soft ground. In this research, the experiments were conducted on a laboratory scale with the various test conditions of mixing method; the angle of mixing wing, mixing speed. Strength and shapes of improved soil of these test conditions of deep mixing method were analysed. From the study, it was found that the mixing conditions affect remarkably to the strength and shapes of improved soils.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.5A
• /
• pp.503-510
• /
• 2009

Latex modified concrete (LMC) is a successful polymer-portland cement concretes, which have been developed and used for many years, in overlaying bridge decks and resurfacing industrial floors. The excellent bond strength to substrate, easy application and high resistance to impact, abrasion, wear, aggressive chemicals and freeze-thaw deterioration have made this material used widely. The objective of this study was to determine experimentally the load-deflection response and ultimate strength of reinforced RC beams. The cracking patterns and the mode of failure were observed. Because of excellent bond strength and repairing effects, the RC beams repaired by LMC at compression or tension zone showed over 100% recovery from damaged structures. The RC beams overlaid by LMC showed significant improvement at load carrying capacity as overlay thickness increases. However, the beams repaired of tension zone without shear stirrups almost showed no strengthen effect, and indicated an interfacial failures. The interfacial behavior was estimated by numerical method adopting the concept of shear flow.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.2A
• /
• pp.113-120
• /
• 2010

The use of Concrete filled circular hollow steel section (CFCHS) members in bridge design is a relatively new concept. The most important part of the design and durability of such structures is the design and the construction of the joints. In the design of recently constructed steel-concrete composite bridges using CFCHS truss girders for the main load carrying structure, the fatigue verification of the tubular spatial truss joints was a main issue. Welded CFCHS joints are very sensitive to fatigue because the geometric discontinuities of the welds lead to a high stress concentration. New research done on the fatigue behaviour of such joints has focused on CFCHS N-joints, directly welded, with finite element analysis method. A commercial software, ABAQUS, is adopted to perform the finite element analysis on the N-joints. This paper is main focused on these topics, including hot spot stress.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.27 no.2
• /
• pp.58-66
• /
• 2023

In this study, cable tension was measured using the vibration method, and a vision-based system was applied as a sensor to measure the displacement response of a cable in a non-contact method. In the vision-based system, the camera is installed in a location that considers the target structure and the field of view of the camera. However, it can be difficult to recognize the control points required to measure the displacement response of a structure as the target structure and other structures such as vehicles may be included in the image at the intended installation location. In this study, a distorted image including a vehicle shows inaccurate results in image analysis due to the installation position of the vision-based system. Accordingly, the image including the vehicle was eliminated by calculating the similarity between the two images. To verify the validity of the method of estimating the cable tension of cable-stayed bridges using the proposed method, the vibration method was applied to cable-stayed bridges in service to measure the tension.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.5A
• /
• pp.823-832
• /
• 2006

To ensure the serviceability requirements of PSC composite girder bridges, it is essential to predict the stresses and deformations of the structure under service load conditions. Stresses and deformations vary continuously with time due to the effects of creep and shrinkage of concrete and relaxation of prestressing steel. The importance of these time-dependent effects is much more pronounced in precast prestressed concrete structures built in stages than in those constructed in one operation. In this paper, time-dependent analyses for PSC composite bridges using 30m standard girders have been conducted considering with the variation of the times of introducing initial prestressing forces and casting concrete. A computer program has been developed for the time-dependent analysis of simple or continuous PSC composite girders and parametric studies are conducted. Based on the numerical results, it is investigated the long-term behaviors of PSC composite girder bridges and discussed the limitations of the current codes for the prestress loss.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.992-1000
• /
• 2022

Heritage buildings (HBs) as structures with historical and architectural relevance that form an integral part of contemporary society. HBs deserve to be protected for as long as possible to retain their significance. Therefore, prioritizing HB maintenance management (HBMM) is pertinent. However, the decision-making process of HBMM can be relatively daunting. The decision-making challenge may be attributed to the multiple 'stakeholders' expectation and requirement which needs to be met. To this end, professionals in the built environment have identified the need to apply the strategic concept of facilities management (FM) in decision making. However, studies exploring the application of FM in decision-making seem lacking. To bridge this gap, this study focuses on developing a framework for strategic decision-making HBMM, which helps achieve HBMM sustainability. At the study's inception, relevant works of literature in the domains of HBMM and FM were conducted. This review helped identify contemporary maintenance practices and their applicability to HBMM. Afterward, a conceptual framework to aid decision-making in HBMM was developed. This framework integrated the concept of FM scope (people, place, process, and technology) while ensuring that decisions and plans were made at strategic, tactical, and operational levels. The conceptual framework presents a holistic guide for professionals in HBMM to ensure that decision processes and outcomes are practical and efficient. It also contributes to the existing body of knowledge on the integration of FM in HBMM. Furthermore, it will help achieve HB sustainability through an effective decision-making process.