This paper proposes a deep learning-based crack evaluation technique using hybrid images. The use of the hybrid images combining vision and infrared images are able to improve crack detectability while minimizing false alarms. In particular, large-scale infrastructures can be inspected by an UAV-mounted hybrid image scanning (HIS)　system, and the corresponding huge amount of data is typically difficult to be analyzed by experts. To automate such making-decision process, deep convolutional neural network is used in this study. As the very first stage, a lab-scale HIS system is developed using a scanning zig and experimentally validated using a concrete specimen with various-size cracks. The test results reveal that macro- and micro-cracks are successfully and automatically detected with minimizing false-alarms.

Recently the interest of Energy have been increasing because of the disaster from abnormal climate. So, energy management solution have been needed. In previous research, we developed building energy information 3D visualization solution. This solution can provide many information associated energy usage and environment. but we don’t know what kind of information is critical for energy management and how to provide the information. This study is aimed to diagnosis system that provide building energy usage and environment information. Measured data, analyzed data and 3D model with energy usage information are placed for verification using Eye-tracking method. Finally it was able to identify what kind of information is more interested at depending on the occupational group. The experimental results can be used as an indicator what kind of information is important to managing building energy.

In this paper, a friction loss estimation method of PS tendon using EM sensor is proposed. PSC girder has many advantages. It is higher in performance and lower in cost design than existing concrete girder. So It is widely used in many structures such as bridges nowadays. However, though in the performance evaluation of PSC girder it is verified whether or not the design tension is applied before construction, the part about the management of the tension loss during construction is insufficient. In this study, the experimental data of friction loss obtained by introducing tensile force on 50m PSC girder and the theoretical values calculated by friction coefficient are compared and analyzed.

The aim of this study is to assess a looseness in a bolt being utilized for connecting components of a structural elements with the help of an Nd:YAG pulsed laser scanning system. Ultrasonic wave propagation imaging (UWPI) of a waveform generated using laser light and recorded by AE sensor was first found. Filtering operation was performed to remove an incident wave. The energy in the reflected wave was further assessed to arrive at a result which indicates structural defect has appeared, i.e., bolt loosening.

In this study, the purpose of the study is to determine the depth of damage caused by early frost damage in concrete slab structures under the conditions of external temperature during winter. In other words, we intend to analyze the depth variation of the early frost damage as the thickness of the concrete slab member changes under the condition of the 3-component binder frequently used in practice. As a result, the thinner the component, the significantly reduced the overall temperature of the concrete. In addition, the thinner the component thickness, the higher the delay in increasing the brightness of the core collected from the concrete member, and the greater the effect on the depth of the early frost damage was on the thinner the component thickness.

Resistivity measurements are carried out on infinite isotropic media such as the surface of the earth. Since the concrete resistivity at the laboratory level is measured on specimens of a specific shape and size, it is necessary to examine the influence of the geometry of the specimen on the resistivity measurement. In this study, the influence of the shape of the concrete specimen on the apparent resistivity was investigated through experiments.

The loss of prestress in cable supported structure is a direct cause of structural deterioration of the structure. Thus, measurement and evaluation of the tensile force acted on a strand consist of the cable system have been a significant technological factor. However, a measurement method of tension for each of strands is not proposed, as well as conservative assessment of cable system is bing adopted in industrial application. This paper proposes a new and effective method for measurement of tensile force in a strand based on ultrasound. Electromagnetic acoustic transducer(EMAT) is used for generation of ultrasound. Tensile force acting on a strand can be measured by characterization of guided waves that propagate along the boundary of geometry. Consequently, proposed method is experimentally verified by some experiments using seven-wire strand.

Recently, interest in the safety and maintenance of the structures is growing. However, due to the low-cost order placed by the ordering organization, the safety diagnosis specialized institution becomes insolvent and many problems have arisen due to insufficient inspection and diagnosis. Therefore, in this study, the current status of bid cost was examined through the survey of the practitioners and case analysis. As a result, Precision safety diagnosis, the criteria cost for structures with a floor area of less than 10,000 ㎡ is lowered to 80 % from the current standard. For structures larger than that, the current criteria cost are applied, but it is deemed necessary to strengthen the rigidity of the criteria cost.

This paper presents a convolutional neural network to automatically conduct the peak picking in frequency domain of structural responses. The peaks in frequency domain have a high potential to be the natural frequencies, which are one of the important indicator to be used for structural health monitoring purposes, such as damage detection, cable tension estimation, and finite element model updating. In general, the peaks with the corresponding natural frequencies are manually selected by the users from the frequency domain. Although this previous approach is possible to simply extract the candidate of natural frequencies, it is inappropriate in the practical applications of the long-term monitoring and the implementation for wireless smart sensor. To overcome the drawbacks, this study proposes the convolutional neural network that can automatically identify the peaks with the corresponding natural frequencies from the frequency domain of structural responses.

This paper proposes real-time image-based damage detection method for concrete structures using deep learning. The proposed method is composed of three steps: (1) collection of a large volume of images containing damage information from internet, (2) development of a deep learning model (i.e., convolutional neural network (CNN)) using collected images, and (3) automatic selection of damage images using the trained deep learning model. The whole procedure of the proposed method has been applied to some figures taken in a real structure. This method is expected to facilitate the regular inspection and speed up the assessment of detailed damage distribution the without losing accuracy.

This paper aims to develop the AE non-destructive testing equipment and signal analysis method for external tendon of PSC (Pre-Stressed Concrete) bridge. The AE NDT equipment, which has developed in this research, is composed of AE sensor, signal receiver, hitting device, driving part and main frame. Defective and non-defective specimens, designed to emulate signal characteristics for external duct with void(25%, 50% and 100%) or not, were constructed and tested to verify the effectiveness of AE NDT equipment. Test results and AE parameters comparisons between defective and non-defective specimens are presented.

In this study, Integrity evaluation of offshore wind turbine substructure was carried out. The strain values obtained by strain gauges circularly installed on upper part of the substructure was converted into vertical and moment load. Considering directions of the moment load through FEM, the most conservative P-M interaction diagram of the model was graphed. Obtained load values were evaluated by utilizing P-M interaction diagram.

In this study, it was evaluated the detection results of ground penetration radar (GPR) by using pixel difference. Experimental tank was made for this purpose. Concrete hume pipe and PE pipe were buried in the tank. The pavement finish of the surface was classified 4th cases. In the case of non-reinforcement concrete pavement, the buried pipe detection was easy than other pavement cases. And it was easy to detect the buried pipe by the difference of the color pixels rather than the black and white pixels.

This paper reviewed the environment of freezing-thawing cycle and snowfall frequency which represents environment of deicing agent in concrete bridges at the same time. The results showed that in terms of complex aging environment, freezing-thawing cycle and salt attack environment should be considered together. As environmental data are used in durability assessment of bridges, the results will be more reliable and practical. In addition, the quantitative evaluation method for complex aging environments will be needed in the future study.

Recent earthquakes in Gyeong-ju and Po-hang have raised concerns about the safety of nuclear power plant structures. In particular, there is a demand for a technique for detecting and evaluating the deterioration that occurs in the concrete which is inaccessible after curing. In this paper, we propose a method for evaluating the reliability of concrete detection equipment using ultrasound, as the ultrasonic tomography technique has been attracting much attention with the detection technique of the inside of concrete.

This paper has a seepage measuring device installed on the water retaining wall at the bottom of the dam, but it has no seepage count and periodically uses underground water handling method to measure the level of seepage. Accordingly, observation of seepage quantities generated by the dam body is used as an important data to assess the safety of the dam body, so it is considered to improve the seepage quantity measuring device.

A fatigue crack occurred in the vicinity of the suspension bridge`s center-stay area is generated. Therefore, the stress and caused of occurrence of each member are analyzed by measurement. When similar cases occur in the future, they shall be utilized as basic data such as research methods and establishment of measures for maintenance.

We have identified the subway of structures as subway station users complained of vibrations from a structures when they walked through middle stairs of escalator. As a result of converting the vibration level to the conversion rate, it was measured at 3.846mm/s(82.7dB) on the B1st floor and 0.966mm/s(70.7dB) on the B2nd floor. These results are higher than the domestic standard of 65dB and lower than the international standard of under 5mm/s. It is felt well with the human body, but the structure is considered to be harmless. Therefore, it is deemded the structure is safe to usue. As the result of measuring the national frequency, the stairs on the B1st floor to be 3.01Hz and the stairs B2nd floor to be 5.36Hz. We consider that the users feel discomfort and anxiety on the B1st floor, where displacement and vibrations are higher.

In the case of railway bridges passing through the urban area, bridge type with excellent noise reduction performance is required. The bridges under development are steel composite through bridges, which is a composite structure of upper flanges with concrete, and the section bridges themselves, which surround the train, have the feature of acting as a sound barrier. In this paper, the performance test of air conduction noise is performed by the 20m full scale model test of new type steel composite through bridge.