• The Journal of Korean Institute of Information Technology
• /
• v.16 no.12
• /
• pp.57-68
• /
• 2018

A system to prevent disasters by collecting and analyzing environmental information such as road surface sedimentation, sinkholes, collapse risk of bridges, temperature and humidity around tram station is continuously monitored by monitoring the condition of road surface when constructing tram which is one of the urban railways. In this paper, we propose a wireless network security management system for tram roads based on LPWA that can recognize risk factors of road surface, bridge and tram station of tram in advance and prevent risk. The proposed system consists of a sensor node that detects the state of the tram road surface, a gateway that collects sensor information, and a safety management system that monitors the safety and environmental conditions of the tram road surface, and applies the low power long distance communication technology. As a result of comparing the proposed system with the LTE system in the field test, it was confirmed that there is no significant difference between the sensor information value and the critical alarm level in the monitoring system.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.237-250
• /
• 2022

Structural health monitoring (SHM) plays an important role in ensuring the safety and functionality of critical civil infrastructure. In recent years, numerous researchers have conducted studies to develop computer vision and machine learning techniques for SHM purposes, offering the potential to reduce the laborious nature and improve the effectiveness of field inspections. However, high-quality vision data from various types of damaged structures is relatively difficult to obtain, because of the rare occurrence of damaged structures. The lack of data is particularly acute for fatigue crack in steel bridge girder. As a result, the lack of data for training purposes is one of the main issues that hinders wider application of these powerful techniques for SHM. To address this problem, the use of synthetic data is proposed in this article to augment real-world datasets used for training neural networks that can identify fatigue cracks in steel structures. First, random textures representing the surface of steel structures with fatigue cracks are created and mapped onto a 3D graphics model. Subsequently, this model is used to generate synthetic images for various lighting conditions and camera angles. A fully convolutional network is then trained for two cases: (1) using only real-word data, and (2) using both synthetic and real-word data. By employing synthetic data augmentation in the training process, the crack identification performance of the neural network for the test dataset is seen to improve from 35% to 40% and 49% to 62% for intersection over union (IoU) and precision, respectively, demonstrating the efficacy of the proposed approach.

• 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.

• Journal of the Korea Concrete Institute
• /
• v.15 no.3
• /
• pp.400-408
• /
• 2003

Chloride ion inside concrete destroys the so-called passive film surrounding reinforcing bars inside concrete so that the so-called salt attack accelerates corrosion which is the most critical factor for durability as well as structural safety of reinforced concrete structures. Recently, as a solution of the salt attack, the ground granulated blast-furnace slag(GGBFS) have been used as binder or blended cement more extensively. In this paper, characteristics of chloride ion diffusion for the GGBFS concrete, which is known to possess better resistance to damage due to the chloride ion penetration than ordinary portland cement(OPC) concrete possesses, are analyzed and a chloride ion diffusion model for the GGBFS concrete is proposed by modifying an existing diffusion model for the OPC concrete. The proposed model is verified by comparing diffusion analysis results using the model accelerated chloride penetration test results for concrete specimens as well as field test results for an RC bridge pier. Then, an optimal resistance condition to chloride penetration for the GGBFS concrete is obtained according to degrees of fineness and replacement ratios of the GGBFS concrete. The result shows that the GGBFS concrete has better resistance to chloride ion penetration than OPC concrete has and the resistance is more affected by the replacement ratio than the degree of fineness of the GGBFS.

• Journal of Korean Society of Disaster and Security
• /
• v.15 no.4
• /
• pp.11-20
• /
• 2022

The general non-destructive inspection method for anchor bolts in Korea applies visual inspection and hammering inspection, but it is difficult to check corrosion or fatigue cracks of anchor bolts in the part included in the foundation or in the part where the nut and base plate are installed. In reality, objective investigation is difficult because inspection is affected by the surrounding environment and individual differences, so it is necessary to develop non-destructive inspection technology that can quantitatively estimate these defects. Inspection of the anchor bolts of domestic road facilities is carried out by visual inspection, and since the importance of anchor bolts such as bridge bearings and fall prevention facilities is high, the life span of bridges is extended through preventive maintenance by developing non-destructive testing technology along with existing inspection methods. Through the development of this technology, non-destructive testing of anchor bolts is performed and as a technology capable of preemptive/active maintenance of anchor bolts for road facilities, practical use is urgently needed. In this paper, the possibility of detecting defects in anchor bolts such as corrosion and cracks and reliability were experimentally verified by applying the ultrasonic test among non-destructive inspection techniques. When the technology development is completed, it is expected that it will be possible to realize preemptive/active maintenance of anchor bolts by securing source technology for improving inspection reliability.

• Journal of the Korea Concrete Institute
• /
• v.20 no.4
• /
• pp.423-430
• /
• 2008

VES-LMC (very-early strength latex-modified concrete) has been widely used as repair material for bridge deck overlay or rehabilitation, because the overlaid or repaired could be opened to the traffic after 3 hours of curing. Although the field performance of VES-LMC generally indicates that it has an excellent bonding to the substrate and shows a long term performance, little quantitative data or research results have been presented in the literature on structural studies. The purpose of this study was to investigate the flexural behavior, interfacial performance, crack propagation, and strengthen effect of RC beam overlaid or repaired by VES-LMC through the 4-point flexural loading test. Two different types of RC beam were fabricated for repair and rehabilitation types. The test result showed that the strengthen effect, in term of flexural stiffness, increases as the depth of repair or overlay increases. More than 40% of stiffness was improved when the depth of repair was up to steel position. However, there was a little difference between 80 mm and 120 mm repaired beam. This means the repair depth must be considered. The interfacial behavior data showed that the repaired or overlaid beams had a little relative displacement. This means that two materials behave comparatively acting together. However, there were two specimens which had large displacement at the interface, because of poor bond strength. This suggested that interface treatment is one of the most important jobs in composite beams.

• Journal of the Korean Geotechnical Society
• /
• v.21 no.5
• /
• pp.187-196
• /
• 2005

Since the allowable bearing capacities of piles in weathered/fractured rock are mainly governed by settlement, the load-displacement behavior of pile should be known accurately. To predict pile head settlement at the design stage, the exact understanding of the load-transfer mechanisms is essential. Therefore, in this research, the load-transfer mechanism of drilled shaft socketed into weathered rock was investigated. For the investigation, five cast-in-place concrete piles with diameters of 1,000 mm were socketed into weathered gneiss. The static axial load tests and the load-transfer measurements were performed to examine the axial resistant behavior of the piles. A comprehensive field/laboratory testing program on weathered rock at the Held test sites was also performed to describe the in situ rock mass conditions quantitatively. And then, the effect of rock mass condition on the load transfer mechanism was investigated. The f-w (side shear resistance-displacement) curve of the pile in moderately weathered rock reached to yielding point at a for millimeter displacements, and after yielding point, the rate of resistance increment dramatically decreased. However, the f-w curve in the highly/completely weathered rock did not show the obvious yielding point, and the resistance gradually increased showing the hyperbolic pattern until relatively high displacement (>15 mm). The q-w (end bearing resistance-displacement) curves showed linear response at least until the base displacement of approximately 10 mm, regardless of rock mass conditions.

• Magazine of the Korea Concrete Institute
• /
• v.10 no.6
• /
• pp.281-289
• /
• 1998

This study has been performed to test the flowability and filling ability of high flowing concrete as well as distribution of aggregate and pore of core specimen, heat of hydration, compressive strength and core strength of concrete. In addition, the resistance to chloride ion penetration and chemical solutionof concrete was tested in order to evaluate the resistance to sea water of concrete and its application of high flowing concrete using blended low heat cement in the field of Seohae Grand Bridge. The properties of high flowing concrete with blended low heat cement were compared with ordinary 25-240-15 concrete using Type V cement. As the results of this study, the flowability and filling ability of high flowing concrete with blended low heat cement is satisfied without vibration. Though the cement content of high flowing concrete with blended low heat cement was 400kg/m$^2$, the rising temperature of it was relatively lower than that of the ordinary 25-240-15 concrete with Type V cement. Also, the compressive of high flowing concrete with blended low heat cement is similar to that of the ordinary 25-240-15 concrete with Type V cement.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.15 no.5
• /
• pp.92-100
• /
• 2011

This paper describes a numerical modeling for deflection calculation using the natural frequency response that is measured acceleration response for concrete bridges. In the formulation of the dynamic deflection, the change amounts and the transformed responses about six kinds of free vibration responses are defined totally. The predicted response can be obtained from the measured acceleration data without requiring the knowledge of the initial velocity and displacement information. The relationship between the predicted response and the actual deflection is derived using the mathematical modeling that is induced by the process of a acceleration test data. In this study, in order to apply the proposed response predicted model to the integration scheme of the natural frequency domain, the Fourier Fast Transform of the deflection response is separated into the frequency component of the measured data. The feasibility for field application of the proposed calculation method is tested by the mode superposition method using the PSC-I bridges superstructures under several cases of moving load and results are compared with the actually measured deflections using transducers. It has been observed that the proposed method can asses the deflection responses successfully when the measured acceleration signals include the vehicle loading state and the free vibration behavior.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.23 no.2
• /
• pp.67-74
• /
• 2019

In this paper the response factor is investigated for middle and small size-RC slab aged bridges. The response factor consists of static and dynamic response factors and is a main parameter in the frequency based-bridge load carrying capacity prediction model. Static and dynamic response factors are determined based on the frequency variation and the impact factor variation respectively between current and previous (or design) states of bridges. Here, the impact factor variation is figured out using the impact factor response spectrum which provides the impact factor according to the natural frequency of bridges. In this study, four actual RC slab bridges aged over 30 years after construction are considered and their span length is 12m. The dynamic loading test in field using a dump truck and eigenvalue analysis with FE models are conducted to identify the current and previous (or design) state-natural frequencies of the bridges, respectively. For more realistic considerations in the moving loading situation, the impact factor response spectrum is developed based on tri-axle moving loads representing the dump truck load distribution and various supporting conditions such as simply supported and both ends fixed conditions. From the results, the response factor is widely ranged from 0.21to 0.91, showing that the static response factor contributes significantly on the results while the dynamic response factor has a small effect on the result. Compared to the results obtained from the impact factor response spectrum based on the single axle-simply supported condition, the maximum percentage difference of the response factors is below 3.2% only.