• Smart Structures and Systems
• /
• v.24 no.5
• /
• pp.567-585
• /
• 2019

In the past two decades, structural health monitoring (SHM) systems have been widely installed on various civil infrastructures for the tracking of the state of their structural health and the detection of structural damage or abnormality, through long-term monitoring of environmental conditions as well as structural loadings and responses. In an SHM system, there are plenty of sensors to acquire a huge number of monitoring data, which can factually reflect the in-service condition of the target structure. In order to bridge the gap between SHM and structural maintenance and management (SMM), it is necessary to employ advanced data processing methods to convert the original multi-source heterogeneous field monitoring data into different types of specific physical indicators in order to make effective decisions regarding inspection, maintenance and management. Conventional approaches to data analysis are confronted with challenges from environmental noise, the volume of measurement data, the complexity of computation, etc., and they severely constrain the pervasive application of SHM technology. In recent years, with the rapid progress of computing hardware and image acquisition equipment, the deep learning-based data processing approach offers a new channel for excavating the massive data from an SHM system, towards autonomous, accurate and robust processing of the monitoring data. Many researchers from the SHM community have made efforts to explore the applications of deep learning-based approaches for structural damage detection and structural condition assessment. This paper gives a review on the deep learning-based SHM of civil infrastructures with the main content, including a brief summary of the history of the development of deep learning, the applications of deep learning-based data processing approaches in the SHM of many kinds of civil infrastructures, and the key challenges and future trends of the strategy of deep learning-based SHM.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.4
• /
• pp.157-166
• /
• 2022

In the case of a die-casting process, defects that are difficult to confirm by visual inspection, such as shrinkage bubbles, may occur due to an error in maintaining a vacuum state. Since these casting defects are discovered during post-processing operations such as heat treatment or finishing work, they cannot be taken in advance at the casting time, which can cause a large number of defects. In this study, we propose an approach that can predict the occurrence of casting defects by defect type using machine learning technology based on casting parameter data collected from equipment in the die casting process in real time. Die-casting parameter data can basically be collected through the casting equipment controller. In order to perform classification analysis for predicting defects by defect type, labeling of casting parameters must be performed. In this study, first, the defective data set is separated by performing the primary clustering based on the total defect rate obtained during the post-processing. Second, the secondary cluster analysis is performed using the defect rate by type for the separated defect data set, and the labeling task is performed by defect type using the cluster analysis result. Finally, a classification learning model is created by collecting the entire labeled data set, and a real-time monitoring system for defect prediction using LabView and Python was implemented. When a defect is predicted, notification is performed so that the operator can cope with it, such as displaying on the monitoring screen and alarm notification.

• Journal of the Korean Wood Science and Technology
• /
• v.36 no.6
• /
• pp.105-112
• /
• 2008

Grading of the urushi lacquer is quite difficult because of large variations depending on origin, growing conditions, time acquisition, storage conditions. It is urgently required to establish a grading system of urushi lacquer by combining traditional method with scientific methods. Traditional grading of urushi lacquer was done by visual inspection of 10 experts who are working on urushi lacquer industry. Common aspects of the experts were color, odor, viscosity, spread properties on Hanji, color and drying properties on glass based the traditional grading system. In addition, rubbing on Hannj and heating with alcohol lamp was also used to grade urushi lacquer. The grading results of 10 experts showed that chinese urushi lacquer (E) of 7.03, japanese urushi lacquer (C) of 6.84, domestic urushi lacquer of (A) of 6.41 and another chinese urushi lacquer (D) of 5.27, and domestic urushi lacquer (B) of 2.50 in descending order. The degree of spread on Hanji was not consistent among 10 experts. These results indicated that the traditional grading system was pretty much personal and required of developing more objective method based on scientific background.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.24 no.2
• /
• pp.164-170
• /
• 2004

Liquid Injection Nozzle(LIN) tube and Calandria tube(CT) in pressurized Heavy Water Reactor (PHWR) are .ross-aligned horizontally. These neighboring tubes can contact each other due to the sag of the calandria tube resulting from the irradiation creep and thermal creep, and fuel load, etc. In order to judge the contact which might be the safety concern, the remote field eddy current (RFEC) technology is applied for the gap measurement in this paper. LIN can be detected by inserting the RFEC probe into pressure tube (PT) at the crossing point directly. To obtain the optimal conditions of the RFEC inspection, the sensitivity, penetration and noise signals are considered simultaneously. The optimal frequency and coil spacing are 1kHz and 200mm respectively. Possible noises during LIN signal acquisition are caused by lift-off, PT thickness variation, and gap variation between PT and CT. The simulated noise signals were investigated by the Volume Integral Method(VIM). Signal analysis on the voltage plane describes the amplitude and shape of LIN and possible defects at several frequencies. All the RFEC measurements in the laboratory were done in variance with the CT/LIN gap and showed the relationship between the LIN gap and the signal parameters by analyzing the voltage plane signals.

• Journal of the Korea Institute of Building Construction
• /
• v.18 no.5
• /
• pp.429-437
• /
• 2018

The aim of the research is to analyze a feasibility of rapid evaluation method for cement fineness by the relation analysis between density measurement using hydrometer and fineness of ordinary Portland cement. Additionally, based on the commercially available cement product, relation between a series of fundamental properties of cement mortar and fineness of cement powder was analyzed. As an experimental result, the actually measured fineness value of cement powder showed a good correlation with the fineness value obtained by hydrometer while there was poor correlation with the fineness value on specification. Especially, the density measurement in three minutes showed the closest relation with cement powder fineness, thus rapid quality evaluation of cement powder can be possible by using the regression equation obtained from the three minutes density measurement. Additionally, there was a high relation between cement powder fineness with a fundamental properties of the cement mortar such as fluidity, air content, setting time, and strength development.

• Journal of Cadastre & Land InformatiX
• /
• v.50 no.1
• /
• pp.163-180
• /
• 2020

In this study, to build a spatial information infrastructure, which is a component of a smart city, a 3D digital twin model in the downtown area was built based on the latest spatial information acquisition technology, the drone. Several analysis models were implemented by utilizing. While the data processing time and quality of the three types of drone photogrammetry software are different, the accuracy of the construction model is ± 0.04 in the N direction and ± 0.03m in the E direction. In the m and Z directions, ± 0.02m was found to be less than 0.1m, which is defined as the allowable range of surveying performance and inspection performance for the boundary point in the area where the registration of the boundary point registration is executed. 1: 500 to 1 of the aerial survey work regulation: The standard deviation, which is the error limit of the photographic reference point of the 600 scale, appeared within 0.14 cm, and it was found that the error limit of the large scale specified in the cadastral and aerial survey was satisfied. In addition, in order to increase the usability of smart city realization using a drone-based 3D urban digital twin model, the model built in this study was used to implement Prospect right analysis, landscape analysis, Right of light analysis, patrol route analysis, and fire suppression simulation training. Compared to the existing aerial photographic survey method, it was judged that the accuracy of the naked eye reading point is more accurate (about 10cm) than the existing aerial photographic survey, and it is possible to reduce the construction cost compared to the existing aerial photographic survey at a construction area of about 30㎢ or less.

• Journal of Korean Society of Rural Planning
• /
• v.27 no.4
• /
• pp.55-70
• /
• 2021

In this study, in the field of remote sensing, where the scope of application is rapidly expanding to fields such as land monitoring, disaster prediction, facility safety inspection, and maintenance of cultural properties, monitoring of rural space and surrounding environment using UAV is utilized. It was carried out to verify the possibility, and the following main results were derived. First, the aerial image taken with an unmanned aerial vehicle had a much higher image size and spatial resolution than the aerial image provided by the National Geographic Information Service. It was suitable for analysis due to its high accuracy. Second, the more the number of photographed photos and the more complex the terrain features, the more the point cloud included in the aerial image taken with the UAV was extracted. As the amount of point cloud increases, accurate 3D mapping is possible, For accurate 3D mapping, it is judged that a point cloud acquisition method for difficult-to-photograph parts in the air is required. Third, 3D mapping technology using point cloud is effective for monitoring rural space and rural resources because it enables observation and comparison of parts that cannot be read from general aerial images. Fourth, the digital elevation model(DEM) produced with aerial image taken with an UAV can visually express the altitude and shape of the topography of the study site, so it can be used as data to predict the effects of topographical changes due to changes in rural space. Therefore, it is possible to utilize various results using the data included in the aerial image taken by the UAV. In this study, the superiority of images acquired by UAV was verified by comparison with existing images, and the effect of 3D mapping on rural space monitoring was visually analyzed. If various types of spatial data such as GIS analysis and topographic map production are collected and utilized using data that can be acquired by unmanned aerial vehicles, it is expected to be used as basic data for rural planning to maintain and preserve the rural environment.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.5
• /
• pp.211-220
• /
• 2022

Recently, research on smart factories triggered by the 4th industrial revolution is being actively conducted. Accordingly, the manufacturing industry is conducting various studies to improve productivity and quality based on deep learning technology with robust performance. This paper is a study on the method of detecting tire surface defects in the visual inspection stage of the tire manufacturing process, and introduces a tire surface defect detection method using a depth image acquired through a 3D camera. The tire surface depth image dealt with in this study has the problem of low contrast caused by the shallow depth of the tire surface and the difference in the reference depth value due to the data acquisition environment. And due to the nature of the manufacturing industry, algorithms with performance that can be processed in real time along with detection performance is required. Therefore, in this paper, we studied a method to normalize the depth image through relatively simple methods so that the tire surface defect detection algorithm does not consist of a complex algorithm pipeline. and conducted a comparative experiment between the general normalization method and the normalization method suggested in this paper using YOLO V3, which could satisfy both detection performance and speed. As a result of the experiment, it is confirmed that the normalization method proposed in this paper improved performance by about 7% based on mAP 0.5, and the method proposed in this paper is effective.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.8 no.7
• /
• pp.475-484
• /
• 2018

The propulsion control device of an electric railway vehicle is a key main component corresponding to an engine of an automobile, and a device for controlling this is a device called a GDU (Gate Drive Unit). Also, when the frequency of failure of the propulsion control system was analyzed, the nonconformity ratio of GDU was the highest. GDU was not able to access core technologies due to the introduction of foreign products, and there were general problems with overall maintenance activities due to discontinuation of GDU of the manufacturer. The GDU has reached the end of its life with 23 to 14 years of long-term use.In order to solve these problems, this study was designed to identify the proper life span by analyzing compatible GDU's acquisition and failure, and to improve the existing system of maintenance focusing on health inspection. Maintenance of the components with a short life span compared to the entire service life is essential. Most foreign parts introduced at the beginning of the construction are not replaced due to technical problems or long-term operation. However, due to the characteristics of railway vehicles with a long life span of more than 25 years, it is necessary to maintain them for a long period of time. The study should be more concrete and empirical. The replacement type GDU of capacitors was able to easily measure the life of the capacitance by removing the capacitor modules, measure the life span of each unit test, and accurately perform preventive maintenance of the capacitor.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1467-1475
• /
• 2023

The public-interest direct payment program involves providing direct payments to agricultural producers and rural residents through public funds, premised on performing public functions such as environmental conservation, stable food supply, and maintaining rural communities via agricultural activities. Scientific estimation of crop cultivation areas and production levels is crucial for formulating agricultural policies linked to regulating food supply, which increasingly impacts the national economy. Conducting comprehensive on-site inspections for compliance monitoring of direct payment programs has shown very low efficiency in relation to budget and time. The expansion of areas subject to compliance monitoring and various challenges in on-site inspections necessitate streamlining current monitoring methods and devising effective strategies. As a solution, the application of Remote Sensing technology and spatial information utilization, allowing swift acquisition of necessary information for policies without overall on-site visits, is being discussed as an efficient compliance monitoring method. Therefore, this study evaluated the potential use of remote sensing for improving operational efficiency in monitoring compliance with public-interest direct payment programs. Using satellite images during farming seasons in Gimje and Hapcheon, vegetation indices and spatial variations were utilized to identify cultivated areas, presence of mixed crops, validated against on-site inspection data.