• 국제학술발표논문집
• /
• The 10th International Conference on Construction Engineering and Project Management
• /
• pp.327-334
• /
• 2024

Bridge inspection is crucial for infrastructure maintenance. Current inspections based on computer vision primarily focus on identifying simple defects such as cracks or corrosion. These detection results can serve merely as preliminary references for bridge inspection reports. To generate detailed reports, on-site engineers must still present the structural conditions through lengthy textual descriptions. This process is time-consuming, costly, and prone to human error. To bridge this gap, we propose a deep learning-based framework to generate detailed and accurate textual descriptions, laying the foundation for automating bridge inspection reports. This framework is built around an encoder-decoder architecture, utilizing Convolutional Neural Networks (CNN) for encoding image features and Gated Recurrent Units (GRU) as the decoder, combined with a dynamically adaptive attention mechanism. The experimental results demonstrate this approach's effectiveness, proving that the introduction of the attention mechanism contributes to improved generation results. Moreover, it is worth noting that, through comparative experiments on image restoration, we found that the model requires further improvement in terms of explainability. In summary, this study demonstrates the potential and practical application of image captioning techniques for bridge defect detection, and future research can further explore the integration of domain knowledge with artificial intelligence (AI).

• 국제학술발표논문집
• /
• The 3th International Conference on Construction Engineering and Project Management
• /
• pp.449-456
• /
• 2009

Image processing has been applied to steel bridge defect recognition since 1990s. Compare to human visual inspection, image processing provides a more objective and accurate way of assessment. Since shade and shadow may sometimes occur when taking bridge coating images, non-uniform illumination problems should be considered. By means of color image processing, this paper aims to mitigate the illumination effect for bridge coating assessment. Furthermore, the adaptable ellipse method (AEM) is proposed to recognize mild rust colors. Finally, AEM will be compared to the K-Means algorithm, a popular recognition method, to show its advantage.

• Structural Engineering and Mechanics
• /
• 제46권5호
• /
• pp.615-627
• /
• 2013

One of the most common defects in reinforced concrete bridge decks is corrosion of steel reinforcing bars. This invisible defect reduces the deck stiffness and affects the bridge's serviceability. Regular monitoring of the bridge is required to detect and control this type of damage and in turn, minimize repair costs. Because the corrosion is hidden within the deck, this type of damage cannot be easily detected by visual inspection and therefore, an alternative damage detection technique is required. This research develops a non-destructive method for detecting reinforcing bar corrosion. Experimental modal analysis, as a non-destructive testing technique, and finite element (FE) model updating are used in this method. The location and size of corrosion in the reinforcing bars is predicted by creating a finite element model of bridge deck and updating the model characteristics to match the experimental results. The practicality and applicability of the proposed method were evaluated by applying the new technique to a two spans bridge for monitoring steel bar corrosion. It was shown that the proposed method can predict the location and size of reinforcing bars corrosion with reasonable accuracy.

• Journal of Welding and Joining
• /
• 제16권6호
• /
• pp.77-85
• /
• 1998

Effects of non-cleaning and cleaning fluxes on the wetting properties and defects at flow soldered joints were investigated. Non-cleaning flux (R-type of 3.3% solid content) and cleaning flux (RMA-type of 15% solid content) were used. Wetting test was accomplished by wetting balance method with changing surface state of wetting specimen, CU. Sn-37%Pb solder was used for wetting test and flow soldering. As experimental results, the wetting time for vertical force from the surface tension being zero was mainly affected by surface state of the wetting specimen. Non-cleaning flux had a good wettability compared with cleaning flux. In case of non-cleaning flux, conveyor speed had a great affection to defects of bridge, icicle, and poor solder.

• Journal of Welding and Joining
• /
• 제19권3호
• /
• pp.267-273
• /
• 2001

In this study, welding phenomena involved in formation of penetrators during high frequency electric resistance welding were investigated. High speed cinematography of the process revealer that a molten bridge between neighboring skelp edges forms at apex point and travels along narrow gap toward to welding point at a speed ranging from 100 to 400 m/min. The bridge while moving along the narrow gap swept away oxide containing molten metal from the gap, providing oxide-free surface for a forge-welding at upsetting stand frequency of the budge formation, travel distance and speed of the bridge were affected by the heat input rate into strip. The travel distance and its standard deviation were found to have a strong relationship with the weld defect density. Based on the observation, a new mechanism of the penetrator formation during HF ERW process is proposed.

• 한국구조물진단유지관리공학회 논문집
• /
• 제2권1호
• /
• pp.98-107
• /
• 1998

There are many weld defects such as surface crack, lack of fusion, and imcomplete penetration in the butt joint of the existing steel bridges. The crack-like defects may significantly reduce the fatigue life of the structure. This paper presents the procedure and the results of the fatigue assessment of the butt joints with weld defect in the existing steel girder bridge. The butt joints with imcomple penetration were instrumented with strain gages to determine the stress histogram under normal traffic. Based on the measured stress histogram the crack propagation analyses were performed for the fatigue assesment. By using the suggested procedure and methodology, one can decide the time of periodic inspection and the necessity of repair of the butt joints with serious weld defects in the existing steel bridge.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2011년도 정기총회 및 추계학술대회 논문집
• /
• pp.815-820
• /
• 2011

The railway bridge of the domestic still has been used steel base such as sperical bearing and pot bearing widely. However, the bearing of steel series is occured corrosion frequently, reduced durability and raised maintenance cost excessively due to the nature of the material. If the elastomeric bearing which is widely used in highway bridge is applied to the railway bridge, it will be able to compensate this defect a lot. In order to apply to the railway bridge used for highway bridge, is needed the control of the bridge ends deflection, lateral displacement and negative reaction. Therefore, the elastomeric bearing can be applied to the railway bridge enough, if installed negative reaction key for control of the bridge ends deflection, improved shear wedge performance for control of the lateral force, adjust the thickness of the elastomeric pad for the minimize deflection, in addition, can be economic design of sub-structures due to damping effect.

• Smart Structures and Systems
• /
• 제13권6호
• /
• pp.901-925
• /
• 2014

The reliability of a Bridge management System depends on the quality of visual inspection and the reliable estimation of bridge condition rating. However, the current practices of visual inspection have been identified with several limitations, such as: they are time-consuming, provide incomplete information, and their reliance on inspectors' experience. To overcome such limitations, this paper presents an approach of automating the prediction of condition rating for bridges based on digital image analysis. The proposed methodology encompasses image acquisition, development of 3D visualization model, image processing, and condition rating model. Under this method, scaling defect in concrete bridge components is considered as a candidate defect and the guidelines in the Ontario Structure Inspection Manual (OSIM) have been adopted for developing and testing the proposed method. The automated algorithms for scaling depth prediction and mapping of condition ratings are based on training of back propagation neural networks. The result of developed models showed better prediction capability of condition rating over the existing methods such as, Naïve Bayes Classifiers and Bagged Decision Tree.

• 대한토목학회논문집
• /
• 제43권2호
• /
• pp.267-275
• /
• 2023

최근 30년 이상 노후화된 국내 인프라의 증가로 한정된 예산 내에서 인프라 유지관리를 위한 정확한 유지관리 비용산출과 그에 따른 적절한 예산분배의 중요성이 증대되고 있다. 이에 본 연구에서는 콘크리트 교량의 대표적인 결함과 이에 대한 보수보강 공법들을 매칭하고 유지보수에 필요한 비용을 산정하였다. 표준품셈과 BMS (Bridge Management System) 데이터 분석을 통해 교량의 보수보강 공법을 분류하였으며, 결함의 위치와 종류, 크기에 따라 결함-공법을 매칭하였다. 그리고 표준품셈을 기준으로 단위당 작업량과 물량을 계산하여 노무비, 경비, 재료비를 구분하여 산출하였다. 서울시 교량 유지보수 내역서와 비교를 통해 평균 예측 정확도가 85.1 %가 나왔으며, 결함의 간단한 조건을 통해 유지보수 비용을 파악할 수 있다. 향후 현장 조건을 고려한 장비 및 야간작업 여부를 추가하여 더 높은 유지보수 비용을 파악할 수 있을 것으로 기대된다.

• Bulletin of the Korean Chemical Society
• /
• 제31권1호
• /
• pp.162-167
• /
• 2010

We investigated the adsorption and desorption characteristics of benzene molecules on $Si(001)-2{\times}n$ surfaces using a variable-low temperature scanning tunneling microscopy. When benzene was adsorbed on a $Si(001)-2{\times}n$ surface at a low coverage, five distinct adsorption configurations were found: tight-binding (TB), standard-butterfly (SB), twisted-bridge, diagonal-bridge, and pedestal. The TB and SB configurations were the most dominant ones and could be reversibly interconverted, diffused, and desorbed by applying an electric field between the tip and the surface. The population ratios of the TB and SB configurations were affected by the benzene coverage: at high coverage, the population ratio of SB increased over that of TB, which was favored at low coverage. The desorption yield decreased with increasing benzene coverage and/or density of vacancy defect. These results suggest that the interaction between the benzene molecules is important at a high coverage, and that the vacancy defects modify the adsorption and desorption energies of the benzene molecules on Si(001) surface.