• Journal of the Society of Disaster Information
• /
• v.17 no.3
• /
• pp.556-567
• /
• 2021

Purpose: In this study, various methods of deep learning-based automatic damage analysis technology were reviewed based on images taken through Unmanned Aerial Vehicle to more efficiently and reliably inspect the exterior inspection and inspection of railway bridges using Unmanned Aerial Vehicle. Method: A deep learning analysis model was created by defining damage items based on the acquired images and extracting deep learning data. In addition, the model that learned the damage images for cracks, concrete and paint scaling·spalling, leakage, and Reinforcement exposure among damage of railway bridges was applied and tested with the results of automatic damage analysis. Result: As a result of the analysis, a method with an average detection recall of 95% or more was confirmed. This analysis technology enables more objective and accurate damage detection compared to the existing visual inspection results. Conclusion: through the developed technology in this study, it is expected that it will be possible to analysis more accurate results, shorter time and reduce costs by using the automatic damage analysis technology using Unmanned Aerial Vehicle in railway maintenance.

• Journal of the Architectural Institute of Korea Structure & Construction
• /
• v.35 no.10
• /
• pp.207-215
• /
• 2019

The aim of the research is analyzing the simple adiabatic temperature rising properties and the heat of hydration based on different placing timing of the mass concrete depending on various replacing ratios of blast furnace slag to comparative analyze the thermal cracking index and cracking possibility. As a result from the experiment, a suggested adiabatic temperature rising equation based on various blast furnace slag replacing ratios can be provide favorable correlation with over 0.99 of $R^2$ value by applying the initial induction period. With this relationship, more accurate prediction of the amount of the hydration heat rising and heating timing, and it is known that there is an approximately $13.1^{\circ}C$ of gap between plain concrete without blast furnace slag and concrete with 80 % of replacing blast furnace slag. To control the setting time and heat rising gap, the mix designs between top and bottom concrete casts were changed 15 cases, and D, E, H, I, and L models of controlling the heat of hydration showed 41.23 to $46.88^{\circ}C$ of core temperature and 0.98 to 1.27 of thermal cracking index. Therefore the cracking possibility was 15 to 52 % of favorable results of possibly controlling both the cracking due to the internal and external retainment and concrete temperature at early age.

• Journal of the Korean Society of Safety
• /
• v.36 no.1
• /
• pp.18-25
• /
• 2021

In many developed countries, such as South Korea, efficiently maintaining the aging infrastructures is an important issue. Currently, inspectors visually inspect the infrastructure for maintenance needs, but this method is inefficient due to its high costs, long logistic times, and hazards to the inspectors. Thus, in this paper, a novel crack inspection approach for concrete bridges is proposed using integrated image processing techniques. The proposed approach consists of four steps: (1) training a deep learning model to automatically detect cracks on concrete bridges, (2) acquiring in-situ images using a drone, (3) generating orthomosaic images based on 3D modeling, and (4) detecting cracks on the orthmosaic image using the trained deep learning model. Cascade Mask R-CNN, a state-of-the-art instance segmentation deep learning model, was trained with 3235 crack images that included 2415 hard negative images. We selected the Tancheon overpass, located in Seoul, South Korea, as a testbed for the proposed approach, and we captured images of pier 34-37 and slab 34-36 using a commercial drone. Agisoft Metashape was utilized as a 3D model generation program to generate an orthomosaic of the captured images. We applied the proposed approach to four orthomosaic images that displayed the front, back, left, and right sides of pier 37. Using pixel-level precision referencing visual inspection of the captured images, we evaluated the trained Cascade Mask R-CNN's crack detection performance. At the coping of the front side of pier 37, the model obtained its best precision: 94.34%. It achieved an average precision of 72.93% for the orthomosaics of the four sides of the pier. The test results show that this proposed approach for crack detection can be a suitable alternative to the conventional visual inspection method.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.10 no.4
• /
• pp.489-497
• /
• 2022

In this study, the fluidity, mechanical properties and microstructure of cement pastes with carbon nanotube (CNT) were experimentally investigated. The 6 types of cement paste mixes with different PCE:CNT and w/b had been manufactured, and several tests including flow, compressive strength, absorption and water porosity were performed on cement pastes with or without CNT.Additionally, microstructural observations such as x-ray diffraction (XRD) and scanning electron microscopy (SEM) were carried out to examine hydrates formed in cement paste with CNT. As a result, it was found that the performance of cement pastes with CNT was better compared to that of control cement paste (OPC) due to both of hydration acceleration effect and filling effect. Furthermore, the SEM images clearly showed that CNT can bridge cracks formed in cement matrix. Conclusively, it is believed that the CNT, if mixed appropriately, could be an option as nono-materials to improve performance of concrete structures.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.10 no.4
• /
• pp.514-522
• /
• 2022

In this study, as part of a study to improve the self-healing performance of concrete structures by applying self-healing capsules made of cementitious materials to cement composite materials, the engineering characteristics of mortars according to PCC(Powder Compacted Capsule) size and mixing ratio were compared and analyzed. For this, fluidity, compressive strength, reload test, carbonation, ultrasonic velocity, and water permeability characteristics were measured according to PCC size and mixing ratio of mortar. As a result of the measurement, the fluidity and compressive strength increased as the mixing ratio of PCC increased, and in the case of the load reload test, the healing ratio increased as the mixing ratio of PCC increased in the 03PC formulation. In the case of water permeability test, it was found that when PCC was used, the reduction ratio of water flow was up to 35 % higher than that of Plain, and when PCC with a size of 0.3 to 0.6 mm was mixed with 15 %, it was found to be effective in improving the crack healing ratio of the mortar.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.5
• /
• pp.567-576
• /
• 2023

In general, RC beam members are designed as flexural members, considering only the bending load. However, in actual buildings, axial and bending load are simultaneously applied due to the continuity between members. As a result, the bending strength of the RC beam member increases, but the displacement decreases, and cracks are mainly concentrated in the center of the beam. Therefore, in this study, the bending performance of both normal and strengthened RC beam using carbon fiber sheets subjected to combined axial and bending load was experimentally evaluated. The carbon fiber sheets were wrapped around the middle of the specimens, and axial and bending load were applied simultaneously to the beams. The magnitude of the axial force and the effects of carbon fiber sheet reinforcement on the deformed shape, bending strength, deflection, and ductility of the RC beams were analyzed. The results show that as the applied axial force increased, the maximum bending strength increased, but the ductility decreased 64%. The bending strength of the strengthened beams increased up to 27%, the maximum deflection decreased around 8% and the ductility increased by up to 43%.

• Journal of Korean Association for Spatial Structures
• /
• v.23 no.3
• /
• pp.95-103
• /
• 2023

With the increasing number of aging buildings across Korea, emerging maintenance technologies have surged. One such technology is the non-contact detection of concrete cracks via thermal images. This study aims to develop a technique that can accurately predict the depth of a crack by analyzing the temperature difference between the crack part and the normal part in the thermal image of the concrete. The research obtained temperature data through thermal imaging experiments and constructed a big data set including outdoor variables such as air temperature, illumination, and humidity that can influence temperature differences. Based on the collected data, the team designed an algorithm for learning and predicting the crack depth using machine learning. Initially, standardized crack specimens were used in experiments, and the big data was updated by specimens similar to actual cracks. Finally, a crack depth prediction technology was implemented using five regression analysis algorithms for approximately 24,000 data points. To confirm the practicality of the development technique, crack simulators with various shapes were added to the study.

• Journal of the Korea Institute of Building Construction
• /
• v.23 no.1
• /
• pp.45-56
• /
• 2023

This study was conducted to examine the feasibility of preparing a durability evaluation plan in watertightness for sealant applied to a PC structure. To this end, 5 types of sealant that equally satisfy the quality standards of the relevant KS standard were selected and tested. Through this testing, it was found that 3 of the 5 types of sealant showed deterioration in watertightness and durability, such as falling off and cracking from the substrate. For the remaining two types, a visual observation showed no significant changes, but additional analysis, confirmed that there was a large difference in the stress reduction rate of the material. Therefore, based on the above results, the need for a performance review in durability between sealant was confirmed, and based on this, the validity of the durability evaluation plan that can be used in product selection was quantitatively confirmed.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.3A
• /
• pp.383-390
• /
• 2008

A Precast Prefabricated Bridge Column using steel tube and prestressing bar was proposed for the application of precast method on substructure. A column specimen designed by the proposed bridge column system was made and performed a quasi-static test. The failure mode appeared to be a flexural failure and there is no damage on column segment connection. And it is good use of the self-centering ability by prestressing force. Test results showed that a column specimen satisfy the earthquake specification, and the structural stability was verified. Nonlinear finite element analysis was performed and compared with the test results. Force-displacement relation and location of crack from the analysis results were compared with the test results and it agreed well. The quantitative analysis was also performed by a parametric study using this modeling technique.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.12 no.6
• /
• pp.119-128
• /
• 2008

In this study, new moment-resisting precast concrete beam-column joint is proposed for moderate seismic regions. It has the connection reinforcing bars, penetrated the joint and lap-spliced with the bottom bars of precast U-shaped PC beam. To evaluate the performance for noncontact lapped splice, experimental and analytical works were conducted. Major variables for tests are the length of lap, the diameter of connection reinforcing bars, and the distance between lapped bars. Analytic research was performed nonlinear finite element method. Analytic research focused on crack pattern, load-deflection curve, comparison of internal force, evaluation of ductility strains of reinforcement bar. Results of experimental and analytical works show that the these variables has much influence on flexural strength and ductility, and joint behavior.