• Journal of the Korea Institute of Building Construction
• /
• v.23 no.2
• /
• pp.165-173
• /
• 2023

This research proposed a model for automatically monitoring the quality of insulation adhesive application in external insulation construction. Upon case implementation, the area segmentation model demonstrated a 92.3% accuracy, while the area and distance calculation accuracies of the proposed model were 98.8% and 96.7%, respectively. These findings suggest that the model can effectively prevent the most common insulation defect, insulation failure, while simultaneously minimizing the need for on-site supervisory personnel during external insulation construction. This, in turn, contributes to the enhancement of the external insulation system. Moving forward, we plan to gather construction images of various external insulation methods to refine the image segmentation model's performance and develop a model capable of automatically monitoring scenarios with a considerable number of insulation materials in the image.

• Nuclear Engineering and Technology
• /
• v.20 no.3
• /
• pp.170-178
• /
• 1988

An automated ultrasonic flaw detection system was developed for thin-walled and short tubes such as Zircaloy-4 tubes used for cladding heavy-water reactor fuel. The system was based on the two channels immersion pulse-echo technique using 14 MHz shear wave and the specially developed helical scanning technique, in which the tube to be tested is only rotated and the small water tank with spherical focus ultrasonic transducers is translated along the tube length. The optimum angle of incidence of ultrasonic beam was 26 degrees, at which the inside and outside surface defects with the same size and direction could be detected with the same sensitivity. The maximum permissible defects in the Zircaloy-4 tubes, i.e., the longitudinal and circumferential v notches with the length of 0.76mm and 0.38mm, respectively and the depth of 0.04 mm on the inside and outside surface, could be easily detected by the system with the inspection speed of about 1 m/min and the very excellent reproducibility. The ratio of signal to noise was greater than 20 dB for the longitudinal defects and 12 dB for the circumferential defects.

• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.1
• /
• pp.229-237
• /
• 2024

The logistics industry is converging with digital technology and growing into various logistics automation systems. However, inspection and loading/unloading, which are mainly performed in logistics work, depend on human resources, and the workforce is shrinking due to the decline in the productive population due to the low birth rate and aging. Although much research is being conducted on the development of automated logistics systems to solve these problems, there is a lack of research and development on load stacking stability, which has the potential to cause significant accidents. In this study, loading boxes with various sizes and positions of the center of gravity were set up, and a method for stacking that with high stability is presented. The size of the loading box is measured using a depth camera. The loading box's weight and center of gravity are measured and estimated by a developed device with four loadcells. The measurement error is measured through various repeated experiments and is corrected using the least squares method. The robot arm performs load stacking by determining the target position so that the centers of gravity of the loading boxes with unbalanced masses with a random sequence are transported in alignment. All processes were automated, and the results were verified by experimentally confirming load stacking stability.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.5
• /
• pp.30-42
• /
• 2022

Due to the increase in construction of tunnels, the burdens of maintenance works for tunnel structures have been increasing in Korea. In addition, the increase of traffic volume and aging of materials also threatens the safety of tunnel facilities, therefore, maintenance costs are expected to increase significantly in the future. Accordingly, automated condition assessment technologies like image-based tunnel scanning system for inspection and diagnosis of tunnel facilities have been proposed. For image-based tunnel scanning system, it is key to create a planar image through stitching of multiple images captured by tunnel scanning system. In this study, performance of feature-based stitching algorithms suitable for stitching tunnel scanning images was evaluated. In order to find a suitable algorithm SIFT, ORB, and BRISK are compared. The performance of the proposed algorithm was determined by the number of feature extraction, calculation speed, accuracy of feature matching, and image stitching result. As for stitching performance, SIFT algorithm was the best in all parts of tunnel image. ORB and BRISK also showed satisfactory performance and short calculation time. SIFT can be used to generate precise planar images. ORB and BRISK also showed satisfactory stitching results, confirming the possibility of being used when real-time stitching is required.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.5
• /
• pp.413-419
• /
• 2022

As the development of the underground space becomes active, safety accidents related to the underground are frequently occurring in recent years. In this regard, the Ministry of Land, Infrastructure and Transport is enforcing the 『Special Act on Underground Safety Management』 (enforced on January 1, 2018, hereafter referred to as the Underground Safety Act). Among the core contents of the Underground Safety Act, underground facilities(water supply, sewage, gas, power, communication, heating) buried underground, underground structures(subway, underpass, underpass, underground parking lot, underground shopping mall, common area), ground (Drilling, wells, geology) of 15 types of underground information can be checked at a glance on a three-dimensional basis by constructing an integrated underground spatial map and using it. The purpose of this study is to develop a program that can quickly inspect the three-dimensional model after creating a three-dimensional underground structure data among the underground spatial integration maps. To this end, we first investigated and reviewed the domestic and foreign status of technology that generates and automatically inspects 3D underground structure data. A quality inspection program was developed. Through this study, it is judged that it will be meaningful as a basic research for improving the quality of underground structures on the integrated map of underground space by automating more than 98% of the 3D model inspection process, which is currently being conducted manually.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.23 no.2
• /
• pp.43-50
• /
• 2019

Purpose The principle of nuclear medicine test is divided into two main categories: competition(radioimmunoassay, RIA) and noncompetitive reaction(Immunoradiometric assay, IRMA). It is known that the curve fitting method, which is commonly used in inspection field, uses Spline interpolation in RIA method and Linear interpolation method in IRMA method. Among them, the insulin test using the IRMA test showed a significant difference, especially at low concentrations, despite the same algorithm of linear interpolation between fully automated radio immunoassay analyzers. In this study, we aim to obtain results from applying two different of algorithm using fully automated radio immunoassay analyzers including Gamma pro, Gamma 10, Cobra, and SR300. Materials and Methods A total of 30 test samples were selected for the test of TSH, ferritin, C-peptide, and insulin serum levels. Test was performed by IRMA method. We compared the difference in the results of applying the linear interpolation method and the spline interpolation method to Gamma Pro, Gamma 10, Cobra, and SR300 equipment. Results Two-way ANOVA was used for statistical analysis. The significance level was applied as P <0.05. The results of TSH, ferritin, C-peptide, and insulin tests were compared between the fully automated radio immunoassay analyzers. There was a significant difference between ferritin, C-peptide, and insulin serum levels(P<0.001). TSH didn't show any significant different between the devices(P=0.29). In the difference between linear and spline interpolation, there was no significant difference between insulin test(P=0.08), TSH test(P=0.81), and Ferritin test(P=0.06). However, C-peptide test showed a significant difference(P=0.03). Especially, the insulin test showed significant difference in lower ranges. As a result of comparing and analyzing the difference between the two interpolation methods, the devices in the low concentration group showed significant difference(P<0.001). Conclusion In case of new equipment in the laboratory it is necessary to recognize that there is a difference in the curve fitting method for each automated radio immunoassay analyzers in the low concentration area when the principle of inspection is IRMA method.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.23 no.6
• /
• pp.38-44
• /
• 2019

A Convolution Neural Network(CNN) model was utilized to detect surface cracks in asphalt concrete pavements. The CNN used for this study consists of five layers with 3×3 convolution filter and 2×2 pooling kernel. Pavement surface crack images collected by automated road surveying equipment was used for the training and testing of the CNN. The performance of the CNN was evaluated using the accuracy, precision, recall, missing rate, and over rate of the surface crack detection. The CNN trained with the largest amount of data shows more than 96.6% of the accuracy, precision, and recall as well as less than 3.4% of the missing rate and the over rate.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.34 no.1
• /
• pp.60-67
• /
• 2014

In this study, an automated cable non-destructive testing(NDT) system was developed to monitor the steel cables that are a core component of cable-stayed bridges. The magnetic flux leakage(MFL) method, which is suitable for ferromagnetic continuum structures and has been verified in previous studies, was applied to the cable inspection. A multi-channel MFL sensor head was fabricated using hall sensors and permanent magnets. A wheel-based cable climbing robot was fabricated to improve the accessibility to the cables, and operating software was developed to monitor the MFL-based NDT research and control the climbing robot. Remote data transmission and robot control were realized by applying wireless LAN communication. Finally, the developed element techniques were integrated into an MFL-based cable NDT system, and the field applicability of this system was verified through a field test at Seohae Bridge, which is a typical cable-stayed bridge currently in operation.

• Journal of Advanced Navigation Technology
• /
• v.25 no.5
• /
• pp.377-383
• /
• 2021

In this paper, we describe the case of automatic test equipment development for hardware verification of stores management computer mounted on aircraft. Recently, the required functions of aircraft have been diversified and the related technologies of avionics equipment have developed, and the types and quantity of interfaces required for avionics equipment have increased. In addition to the existing old stores, the stores management computer also needs to control the interface in large quantities as the requirements for the new stores are added. For this reason, the time and manpower required for the inspection of avionic equipment are also increasing, and if the test process of avionic equipment can be automated and unmanned, more efficient inspection system operation will be possible. Therefore, this paper introduces the case of designing test software and test scenario to automate the structural design contents and verification process of test equipment required for the verification of hardware function of stores management computer.

• Nuclear Engineering and Technology
• /
• v.53 no.2
• /
• pp.657-665
• /
• 2021

Nondestructive evaluation methods play an important role in ensuring component integrity and safety in many industries. Operator fatigue can play a critical role in the reliability of such methods. This is important for inspecting high value assets or assets with a high consequence of failure, such as aerospace and nuclear components. Recent advances in convolution neural networks can support and automate these inspection efforts. This paper proposes using residual neural networks (ResNets) for real-time detection of corrosion, including iron oxide discoloration, pitting and stress corrosion cracking, in dry storage stainless steel canisters housing used nuclear fuel. The proposed approach crops nuclear canister images into smaller tiles, trains a ResNet on these tiles, and classifies images as corroded or intact using the per-image count of tiles predicted as corroded by the ResNet. The results demonstrate that such a deep learning approach allows to detect the locus of corrosion via smaller tiles, and at the same time to infer with high accuracy whether an image comes from a corroded canister. Thereby, the proposed approach holds promise to automate and speed up nuclear fuel canister inspections, to minimize inspection costs, and to partially replace human-conducted onsite inspections, thus reducing radiation doses to personnel.