Recently, in the building and infrastructure fields, studies on defect detection methods using deep learning have been widely implemented. For robust automatic recognition of defects in buildings, a sufficiently large training dataset is required for the target defects. However, it is challenging to collect sufficient data from degrading building structures. To address the data shortage and imbalance problem, in this study, a data augmentation method was developed using a generative adversarial network (GAN). To confirm the effect of data augmentation in the defect dataset of old structures, two scenarios were compared and experiments were conducted. As a result, in the models that applied the GAN-based data augmentation experimentally, the average performance increased by approximately 0.16 compared to the model trained using a small dataset. Based on the results of the experiments, the GAN-based data augmentation strategy is expected to be a reliable alternative to complement defect datasets with an unbalanced number of objects.

The need for maintenance is increasing due to the aging of facilities. In this study, we proposed a crack width measurement method for images collected at safe distances using UAVs (Unmanned Aerial Vehicles). It is a method of measuring the widths of cracks using a high-resolution (VDSR) algorithm, which measures by increasing the resolution of images taken at 3 m intervals on the wall where cracks exist. In addition, the crack width measurement value was compared with a general photographed image and a high-resolution conversion image. As a result, it was confirmed that the crack width measurement of the image to which the high resolution was applied was similar to the actual measured value. These results can help improve the practical applicability of UAVs for facility safety inspections by overcoming the limits of camera resolution and distances between UAVs and facilities introduced in the facility safety inspection. However, more detailed image resolution is required to quantitatively measure the crack width; we intend to improve this through additional studies.

The simultaneous presence of multiple heavy trucks on road bridges causes a higher stress to the structural members of bridges than the presence of a single heavy truck. Truck traffic data acquired using weigh-in-motion systems are typically used to assess the multiple-presence probability for side-by-side and following trucks. A number of high-speed weigh-in-motion (HS-WIM) systems are installed in the Korean Expressway Network to control overloaded vehicles and obtain long-term truck weight data. In this study, the multiple-presence probabilities for following and side-by-side trucks were determined using data from two HS-WIM sites. The correlation probability between the gross vehicle weights (GVWs) of successive trucks was also calculated. To determine the characteristics of heavier truck loads, the multiple-presence probabilities for the overweight trucks, which exceed the legal weight limit, were calculated separately. The analysis of the HS-WIM data showed that the multiple-presence probabilities of the trucks increased with the headway distance of following or side-by-side trucks, and the probability of following truck events was lower than that of side-by-side truck events. The probability of side-by-side truck events increased with the increase of daily truck traffic (DTT), whereas the probability of following truck events was only slightly affected by the DTT. The full correlation probabilities of the GVW for the following and side-by-side trucks were low.

In areas of civil engineering, the resilient friction base isolator (R-FBI) system has been used due to its enhanced isolation performance under seismic excitations. However, because nonlinear behavior of the R-FBI should be reflected in seismic design, effective stiffness (K_eff) of the R-FBI is uniformly applied at both peak ground acceleration (PGA) of 0.08 g and 0.154 g which use a multimodal response spectrum (RS) method analysis. For rational seismic design of bridges, it should be required to evaluate the dynamics of the R-FBI from in-field tests and to improve the seismic design procedure based on the performance level of the bridges. The objective of this study is to evaluate the dynamics of the R-FBI and to suggest the performance-based seismic design method for cable-supported bridges with the R-FBI. From the comparison between the experiments’ results and modal shape analyses, the modal shape analyses using primary (K_u) or infinite stiffness (fixed end) showed a great agreement with the experimental results compared to the application of K_eff in the shape analysis. Additionally, the RS or nonlinear time history method analyses by the PGA levels should be applied by reflecting the dynamic characteristics of the R-FBI for the reasonable and efficient seismic design.

A number of bridges on Korean highways have been damaged by fires in recent years. Most of these fires were caused by tanker trucks. In 2010, a gasoline tanker truck parked under a steel box girder bridge caught fire and caused partial collapse of the bridge. To protect bridges against fires, a bridge fire risk assessment procedure and fire-resistant design guidelines were developed in this study. The fire risk assessment procedure is composed of three main steps: Preliminary Risk Analysis (PRA), Simplified Risk Analysis (SRA), and Detailed Risk Analysis (DRA). The fire occurrence probability, vulnerability, and importance of bridges are considered in the risk assessment procedure. For high-risk bridges, fire-resistant designs must be implemented. Two important design considerations are bridge clearance height and under-bridge conditions.

The appropriate maintenance of highway roads is critical for the safe operation of road networks and conserves maintenance costs. Multiple methods have been developed to investigate the surface of roads for various types of cracks and potholes, among other damage. Like road surface damage, the condition of expansion joints in concrete pavement is important to avoid unexpected hazardous situations. Thus, in this study, a new system is proposed for autonomous expansion joint monitoring using a vision-based system. The system consists of the following three key parts: (1) a camera-mounted vehicle, (2) indication marks on the expansion joints, and (3) a deep learning-based automatic evaluation algorithm. With paired marks indicating the expansion joints in a concrete pavement, they can be automatically detected. An inspection vehicle is equipped with an action camera that acquires images of the expansion joints in the road. You Only Look Once (YOLO) automatically detects the expansion joints with indication marks, which has a performance accuracy of 95%. The width of the detected expansion joint is calculated using an image processing algorithm. Based on the calculated width, the expansion joint is classified into the following two types: normal and dangerous. The obtained results demonstrate that the proposed system is very efficient in terms of speed and accuracy.