• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.18 no.2
• /
• pp.178-186
• /
• 2009

Most of automotive plastic parts are injection molding products. Inspection of total product is impossible, because number of product to inspect is too many and various. Condition-based Monitoring was proposed to decrease cost and time for inspecting. In this research, a system that predicts quality of part at fabrication point of time, and confirms informations through the internet was developed. Cavity sensors were installed inside of mold, and gathered signals as measuring, and through this process Sensor-based Monitoring system can be observed manufacturing of a part. Monitoring system transmits signals to client through the internet, and finally developed system provides manufacturing informations and predictions of quality as web-based monitoring.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.12 no.3
• /
• pp.181-194
• /
• 1992

Deformations of a prototype vacuum chamber for the Storage Ring of the Pohang Light Source Project, due to both welding and baking, have been measured using the Optical Tooling Technique. The measurements aim for the acquisition of data for inspection of the chamber design and for the establishment of positional relationship with the components surrounding the chamber. The effectiveness of the Optical Tooling Technique, as a replacement for the conventional mechanical precision measurement, has been proved by the successful measurements of the vacuum chamber deformations.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2018.11a
• /
• pp.85-86
• /
• 2018

In this study, we previously conducted a quick evaluation of cement powder map using mesiline and hydrometer. The experiment also confirmed the possibility of rapid quality evaluation of cement powder. In this study, further studies have been conducted to apply speed and cost more economical than conventional methods, and the possibility of applying this research is to be analyzed. The result of the experiment was 500 mL of a bottled water bottle with a solid edge for measurement convenience, and the hydrometer was determined to be B type. In addition, density values of each other by powder during the same time period are considered to be measurable, indicating large differences.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.7
• /
• pp.1100-1104
• /
• 2017

A detector-based approach shows the limited performances for the defect inspections such as shallow fine cracks and indistinguishable defects from background. Deep learning technique is widely used for object recognition and it's applications to detect defects have been gradually attempted. Deep learning requires huge scale of learning data, but acquisition of data can be limited in some industrial application. The possibility of applying CNN which is one of the deep learning approaches for surface defect inspection is investigated for industrial parts whose detection difficulty is challenging and learning data is not sufficient. VOV is adopted for pre-processing and to obtain a resonable number of ROIs for a data augmentation. Then CNN method is applied for the classification. Three CNN networks, AlexNet, VGGNet, and mofified VGGNet are compared for experiments of defects detection.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2021.11a
• /
• pp.23-24
• /
• 2021

Since 2011, apartment houses account for about 41% of the fires in residential facilities for the past 10 years. Fire-resistant performance of fire doors is becoming more important to prevent the spread of fire in apartment houses. This research analyzed the structure of fire door through each 10 DB based on the quality inspection report of Continuous Acquisition & Life-cycle Support(CALS) from 2016 to 2020, which passed the fire performance test based on the laws and notices of domestic fire door. Therefore, based on the results of the analysis of DB in the future, we will conduct a study on structural improvement and addition for fireproof performance improvement of fire door.

• Journal of the Korean Society of Industry Convergence
• /
• v.26 no.5
• /
• pp.785-792
• /
• 2023

Because hyperspectral imaging provides detailed spectral information across a broad range of wavelengths, it can be utilized in numerous applications, including environmental monitoring, food quality inspection, medical diagnosis, material identification, art authentication, and crime scene analysis. However, hyperspectral images often contain various types of distortions due to the environmental conditions during image acquisition, which necessitates the proper removal of these distortions through a data preprocessing process. In this study, a preprocessing method was investigated to effectively correct the distortion caused by artificial light sources used in indoor hyperspectral imaging. For this purpose, a halogen-tungsten artificial light source was installed indoors, and hyperspectral images were acquired. The acquired images were then corrected for distortion using a preprocessing that does not require complex auxiliary equipment. After the corrections were made, the results were analyzed. According to the analysis, a statistical transformation technique using mean and standard deviation with reference to a reference signal was found to be the most effective in correcting distortions caused by artificial light sources.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.20 no.6
• /
• pp.538-544
• /
• 2000

A phased array ultrasonic nondestructive inspection system is being developed to obtain images of the interior of steel structures by modifying a medical ultrasound imaging system. The medical system consists of 64 individual transceiver channels that can drive 128 array elements. Several modifications of the system were required mainly due to the change of sound speed. It was necessary to fabricate array transducers for steel structure and to obtain A-scan signal that is necessary for the nondestructive testing. Boundary diffraction wave model was used for the prediction of radiation beam field from array transducers, which provided guidelines to design array transducers. And a RF data acquisition board was fabricated for the A-scan signal acquisition along a selected un line within an image. For the proper beam forming in the transmission and reception for steel structure, delay time was controlled. To demonstrate the performance of the developed system and fabricated transducers, images of artificial specimens and A-scan signals for selected scan lines were obtained in a real time fashion.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.31 no.4
• /
• pp.311-319
• /
• 2013

As heavy rains occur more frequently due to the recent climate change, slope collapses are increasing, and damage to human life and properties is accordingly increasing every year. The most proper method to take preventive measures against slope collapses is to remove the cause after understanding the cause of slope collapse in advance, and for such, slope safety inspection is implemented for preventive purposes, to investigate the cause, and as a measure for restoration. Thus, this Research was able to reach the following conclusion after utilizing LiDAR, which obtains detailed topographic information in a short period of time with point cloud data on slopes subject to safety inspection. First, as a result of analyzing the errors after installing a check point in the subject area, the RMSE of the horizontal location error appeared to be ${\pm}2.2cm$ and the RMSE of the vertical location error appeared to be ${\pm}3.0cm$, which shows a practically satisfactory result. Second, the economic feasibility was outstanding and obtaining accurate topographic information was available. Third, an area once scanned allowed to accurately obtain an unprescribed cross-sectional diagram in a short period of time, thus, appeared to be convenient for experts to detect dangerous sections.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.25 no.6
• /
• pp.555-567
• /
• 2023

The cracks in the tunnel are currently determined through visual inspections conducted by inspectors based on images acquired using tunnel imaging acquisition systems. This labor-intensive approach, relying on inspectors, has inherent limitations as it is subject to their subjective judgments. Recently research efforts have actively explored the use of deep learning to automatically detect tunnel cracks. However, most studies utilize public datasets or lack sufficient objectivity in the analysis process, making it challenging to apply them effectively in practical operations. In this study, we selected test datasets consisting of images in the same format as those obtained from the actual inspection system to perform an objective evaluation of deep learning models. Additionally, we introduced ensemble techniques to complement the strengths and weaknesses of the deep learning models, thereby improving the accuracy of crack detection. As a result, we achieved high recall rates of 80%, 88%, and 89% for cracks with sizes of 0.2 mm, 0.3 mm, and 0.5 mm, respectively, in the test images. In addition, the crack detection result of deep learning included numerous cracks that the inspector could not find. if cracks are detected with sufficient accuracy in a more objective evaluation by selecting images from other tunnels that were not used in this study, it is judged that deep learning will be able to be introduced to facility safety inspection.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.13 no.4
• /
• pp.25-31
• /
• 1994

A system for EMAT, which generates ultrasound by electro-magnectic forces and performs nondestructive testing in noncontact, was established. By linking it with a 3 axis scanning system and a data acquisition and processing system the automation of EMAT testing was attempted. A EMAT sensor was fabricated and the directivity pattern of it was measured. To be suitable automation, it has a transmitter and a receiver in one case and the main beam direction of it can be controlled by the frequency of driving signal. A program which controls the EMAT system, the 3 axis scanner and the data acquisition and processing system was developed. It also processes acquired data and displays the processing results. IBM-PC/AT compatible PC was used as main controller and the stratage of the program is emulation of real devices on the PC monitor. To provide the performance of the established EMAT system, two aluminium blocks containing artificial flaws and a welded aluminium block were tested. The result of the tests were satisfactory.