• Korean Journal of Construction Engineering and Management
• /
• v.21 no.6
• /
• pp.46-55
• /
• 2020

The maintenance cost for highway pavement is gradually increasing due to the continuous increase in road extension as well as increase in the number of old routes that have passed the public period. As a result, there is a need for a method of minimizing costs through preventative grievance Preventive maintenance requires the establishment of a strategic plan through accurate prediction old Highway pavement. herefore, in this study, the XGBoost among machine learning classification-based models was used to develop a highway pavement damage prediction model. First, we solved the imbalanced data issue through data sampling, then developed a predictive model using the XGBoost. This predictive model was evaluated through performance indicators such as accuracy and F1 score. As a result, the over-sampling method showed the best performance result. On the other hand, the main variables affecting road damage were calculated in the order of the number of years of service, ESAL, and the number of days below the minimum temperature -2 degrees Celsius. If the performance of the prediction model is improved through more data accumulation and detailed data pre-processing in the future, it is expected that more accurate prediction of maintenance-required sections will be possible. In addition, it is expected to be used as important basic information for estimating the highway pavement maintenance budget in the future.

• Journal of the Korea Institute of Building Construction
• /
• v.17 no.6
• /
• pp.545-557
• /
• 2017

The study is about the efficient alternative to concrete surface in the field of visual inspection technology for deteriorated infrastructure. By combining industrial drones and deep learning based image analysis techniques with traditional visual inspection and research, we tried to reduce manpowers, time requirements and costs, and to overcome the height and dome structures. On board device mounted on drones is consisting of a high resolution camera for detecting cracks of more than 0.3 mm, a lidar sensor and a embeded image processor module. It was mounted on an industrial drones, took sample images of damage from the site specimen through automatic flight navigation. In addition, the damege parts of the site specimen was used to measure not only the width and length of cracks but white rust also, and tried up compare them with the final image analysis detected results. Using the image analysis techniques, the damages of 54ea sample images were analyzed by the segmentation - feature extraction - decision making process, and extracted the analysis parameters using supervised mode of the deep learning platform. The image analysis of newly added non-supervised 60ea image samples was performed based on the extracted parameters. The result presented in 90.5 % of the damage detection rate.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• autumn
• /
• pp.539-542
• /
• 2002

Crack sealing is a maintenance procedure that is commonly used to reduce pavement degradation. If cracks in pavements are not sealed, surface water penetration can reduce the strength of the sub-base layers, which can result in increased deflections of the pavement. Reduced strength of the sub-base also accelerates the deterioration of the surface, due to development of greater cracking and potholes. Crack sealing is performed to reduce water and debris penetration, thereby helping to maintain pavement structural capacity and limiting future degradation. The process of sealing cracks in pavements is however dangerous, costly, and labor-intensive operation. Labor turnover and training are increasing problems related to crack sealing crews, and as traffic volumes increase. Automating crack sealing can reduce labor and road user costs, improve work quality, and decrease worker exposure to roadway hazards. The main objective of this research is to develop an automated system for sealing cracks in pavement. Extension of the algorithms and tools presented in this research is also recommended for future study.

• Journal of Korean Society of Steel Construction
• /
• v.25 no.3
• /
• pp.307-320
• /
• 2013

This paper proposes a new hybrid support structure by the driven piles which removes disadvantages of the existing type of support structure for offshore wind turbines. The hybrid type of support structure is combined with concrete cone and steel shaft, and is supported not only by gravity type foundations but also by driven piles. For three dimensional analysis of the huge and thick concrete structure, a solid-shell element that is capable of exact modeling and node interpolations of stresses is developed. By applying wave theory of stream function and solid-shell element in XSEA simulation software for fixed offshore wind turbines, a quasi-static analysis and natural frequency analysis of proposed support structure are performed with the environmental condition on Southwest Coast in Korea. In the result, lateral displacement is not exceed allowable displacement and a superiority of dynamic behavior of new hybrid support structure is validated by natural frequency analysis. Consequently, the hybrid support structure presented in this study has a structural stability enough to be applied on real-site condition in Korea. The optimized structures based on the preliminary design concept resulted in an efficient structure, which reasonably reduces fabrication costs.

• Journal of Korean Society of Transportation
• /
• v.34 no.5
• /
• pp.465-475
• /
• 2016

Since inaccurate demand estimation for recent urban rail construction may result in financial burden to cities, precise prediction for operating cost as well as construction costs is necessary to avoid or reduce budget loss of the local or central government. The operating cost is directly related to the public fare and affect a policy to determine the rate system. Therefore, there is a pressing need to develop an estimating model for reliable operating cost of urban railway. This study introduces a new model to estimate the operating cost with new variables. It provides a better prediction in accuracy and reliability compared to the existing model, considering the feature of urban railway. For verification of our model, railway operation data from a few cities for the last five years were comprehensively examined to determine variables that affect the operating cost. The operating cost was estimated in a dummy regression model using five independent variables, which were average distance between stations, daily trains distance, total passenger capacity of a train in a train, driving mode(manned/unmanned), and investment type(financial/private).

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.11
• /
• pp.731-739
• /
• 2017

As Additive Manufacturing (AM), so-called 3D printing technology, has become visualized, its potential for Mass-Customization, production costs and time savings has extended the scope of utilization to the architecture domain. Several cases that produced facilities, building elements and components using 3D printing technology have been announced mainly on the outside. There is also the development of foundation technologies including 3D printing-specific materials and equipment in Korea. As 3D printing technology in the architecture domain is currently in the early stages of adoption, realistic and systematic strategies are needed to advance it to the commercialization stages, considering the current circumstances of the industry. With this background, this study surveyed experts to investigate the status of the perception of 3D printing technology for adoption in domestic architecture industry. 3D printing technology is expected to be commercialized in areas of irregular-shape buildings and interior markets rather than general construction area. 3D printed products expected to be commercialized are limited to the level of building elements and the aesthetic factor is regarded as the most competitive factor. To enhance the possibility of the commercialization of 3D printed products, the 3D printing-specific construction method, related policies and systems are required along with the performance and stability of the materials and equipment.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.7
• /
• pp.425-433
• /
• 2016

The construction of a light rail transit (LRT) system is a large and complex infrastructure project involving hundreds of billions of won in construction costs for a single route, and it is very important to carry out such a project from a life-cycle perspective because of its long-term operation. Systems engineering is a means and methodology to successfully implement customers' needs, and it is useful in large projects such as light rail transit. An application model called Systems Engineering for Light Rail Transit (SELRT) was developed to support systems engineering activities in light rail transit projects. In order to utilize SELRT, it is necessary to ensure that system requirements are met. As such, in this paper, we present a verification procedure and architecture based on a systems engineering-based methodology, thereby identifying the system requirements and deriving the verification requirements to confirm the SELRT model for the proposed method. The results show that the traceability of the system requirements and verification requirements, the verification method for each requirement, and the demonstration results for computerized tools are mutually connected, and that the initial requirements are clearly implemented in the SELRT. The proposed method is valid for verifying the SELRT, which can also be utilized in a LRT project.

• Korean Journal of Construction Engineering and Management
• /
• v.18 no.4
• /
• pp.57-66
• /
• 2017

Using bidding data collected from the World Bank's open database, this research performed a series of competitive analyses of the major countries that have participated in the Bank's engineering consulting services contracts in Vietnam. The goal of the analysis was to evaluate the performance of Korean engineering firms to date, and provide strategic recommendations for future projects. Results showed that Korean firms had a high bid acceptance rate, comparable to major developed countries. The success was attributed to the high technical scores in the selection process. Comparatively, financial scores were not competitive and inferior to developing countries such as China and India. Results of a 'Skitmore' analysis revealed that Korea was competitive in medium size projects and were situated between developed and developing countries. Korea thus needs to increase participation in basic and detailed design services, 2) improve labor costs through 'localization' and latest technologies, and 3) and venture into larger sized projects.

• International Journal of Highway Engineering
• /
• v.13 no.1
• /
• pp.139-148
• /
• 2011

Asphalt concrete overlay method is used by general maintenance and rehabilitation of construction for aged concrete pavement in Korea. However, in case of the AC overlay method to extend service life of the existing concrete pavements, various distresses of reflection crack, pothole and rutting are the typical problems of the asphalt overlay on existing concrete pavement since it has different physical characteristics between asphalt overlay and existing concrete pavement. To achieve this, application of concrete overlay method is required instead of AC overlay method. Concrete overlay method has advantages that can reduce maintenance cycle and costs since it has excellent bearing value for heavy vehicles and no rutting. However, technical problems of detour road construction, traffic control and other disadvantages happened by long curing time. Thus, in this study and experimental research were launched to evaluate the workability, durability and resistance against environmental loading of Very Rapid Hardening Acrylic Polymer Modified Concrete(VRH-APMC) for application of bonded concrete overlay method. Test results showed that the compressive and bond strength were exceed 21MPa and 1.4MPa of target strength after four hours for rapid traffic opening properties. And tests of resistance against environmental loading results showed that VRH-APMC secured excellent durability. Thus, it was known that VRH-APMC was suitable material for large scale bonded concrete overlay method, and it was possible to use maintenance and rehabilitation method which needs enough workability and rapid traffic opening.

• Journal of Cadastre & Land InformatiX
• /
• v.47 no.1
• /
• pp.111-126
• /
• 2017

Small-scale UAS(Fusion technique of Unmanned Aerial Vehicles platform and Sensors, 'sUAS') opens various new applications in construction fields and so becoming progressively common due to the considerable potentials in terms of accuracy, costs and abilities. The purpose of this study is that the investigation of the validation on the utilization of sUAS for earth stockpile volume calculations on sites. For this, generate 3D models(DSM) with sUAS aerial images on an cone shaped soil stockpile approximately $270m{\times}300m{\times}20m$, which located at Baegot Life Park in Siheung-si, compared stockpile volume estimates produced by sUAS image analysis, against volume estimates obtained by GNSS Network-RTK ground surveying method which selected as the criteria of earth stockpile volume. The result through comparison and examination show(demonstrate) that there was under 2% difference between the volume calculated with the GNSS Network RTK data and the sUAV data, especially sUAS imaged-based volume estimate of a stockpile can be greatly simplified, done quickly, and very cost effective over conventional terrestrial survey methods. Therefore, with consideration of various plan to assess the height of vegetation, sUAS image-based application expected very useful both volume estimate and 3D geospatial information extraction in small and medium-sized sites.