• Journal of The Korean Society of Agricultural Engineers
• /
• 제63권1호
• /
• pp.27-35
• /
• 2021

KRC (Korea Rural Community Corporation) is in charge of about 3,400 agricultural reservoirs out of 17,240 agricultural reservoirs, and automatic water level gauges in reservoirs and canals were installed to collect reservoir and canal water level data from 2010. In this study, 10-minute water level data of 173 reservoir irrigation canals from 2016 to 2018 are collected, and discharge during irrigation season was calculated using rating curves. For estimation of water supply, irrigation water requirement was calculated with HOMWRS (Hydrological Operation Model for Water Resources System), and the summation of reservoir water storage decrease was calculated with daily reservoir storage data from RAWRIS (Rural Agricultural Water Resource Information System). From the results, the total yearly amount of irrigation water supply showed less than 10% difference than the irrigation water requirement. The regional analysis revealed that reservoirs in Jeollanam-do and Chungcheongnam-do supply greater irrigation water than average. On the contrary, reservoirs in Gyeongsangnam-do and Chungcheongbuk-do supply less than others. This study was conducted with a limited number of reservoirs compared to total agricultural reservoirs. Nevertheless, it can indicate irrigation water supply from agricultural reservoirs to provide information about agricultural water use for irrigation.

• Journal of the Microelectronics and Packaging Society
• /
• 제30권4호
• /
• pp.69-78
• /
• 2023

With the rapid growth of artificial intelligence, the demand for semiconductors is enormously increasing everywhere. To ensure the manufacturing quality and quantity simultaneously, the importance of automatic defect detection during the packaging process has been re-visited by adapting various deep learning-based methodologies into automatic packaging defect inspection. Deep learning (DL) models require a large amount of data for training, but due to the nature of the semiconductor industry where security is important, sharing and labeling of relevant data is challenging, making it difficult for model training. In this study, we propose a new framework for securing sufficient data for DL models with fewer computing resources through a divide-and-conquer approach. The proposed method divides high-resolution images into pre-defined sub-regions and assigns conditional labels to each region, then trains individual sub-regions and boundaries with boundary loss inducing the globally coherent and seamless images. Afterwards, full-size image is reconstructed by combining divided sub-regions. The experimental results show that the images obtained through this research have high efficiency, consistency, quality, and generality.

• Structural Engineering and Mechanics
• /
• 제91권5호
• /
• pp.443-457
• /
• 2024

At present, the traditional concrete surface inspection methods based on artificial vision have the problems of high cost and insecurity, while the computer vision methods rely on artificial selection features in the case of sensitive environmental changes and difficult promotion. In order to solve these problems, this paper introduces deep learning technology in the field of computer vision to achieve automatic feature extraction of structural damage, with excellent detection speed and strong generalization ability. The main contents of this study are as follows: (1) A method based on DeepLabV3+ convolutional neural network model is proposed for surface detection of post-earthquake structural damage, including surface damage such as concrete cracks, spaling and exposed steel bars. The key semantic information is extracted by different backbone networks, and the data sets containing various surface damage are trained, tested and evaluated. The intersection ratios of 54.4%, 44.2%, and 89.9% in the test set demonstrate the network's capability to accurately identify different types of structural surface damages in pixel-level segmentation, highlighting its effectiveness in varied testing scenarios. (2) A semantic segmentation model based on DeepLabV3+ convolutional neural network is proposed for the detection and evaluation of post-earthquake structural components. Using a dataset that includes building structural components and their damage degrees for training, testing, and evaluation, semantic segmentation detection accuracies were recorded at 98.5% and 56.9%. To provide a comprehensive assessment that considers both false positives and false negatives, the Mean Intersection over Union (Mean IoU) was employed as the primary evaluation metric. This choice ensures that the network's performance in detecting and evaluating pixel-level damage in post-earthquake structural components is evaluated uniformly across all experiments. By incorporating deep learning technology, this study not only offers an innovative solution for accurately identifying post-earthquake damage in civil engineering structures but also contributes significantly to empirical research in automated detection and evaluation within the field of structural health monitoring.

• Journal of the Korean Society for Nondestructive Testing
• /
• 제23권1호
• /
• pp.30-37
• /
• 2003

In order to replace the manual ultrasonic testing(UT) with an automated UT(AUT), a scanner which enables us to control the positions of a transducer is essential. Encoders have been commonly used to obtain the position information from the conventional scanners controlled by motor. Encoders have various advantages in many aspects. However, if the slip of motor wheel occurs during scanning, various errors are involved in the position accuracy. Thus, the position information of encoders becomes meaningless in case of slip. The reliability of AUT results nay become serious problem. Hence, slip must be avoided, but it can not be completely avoided at present time. In this paper, a new idea that surface wave is used to solve this problem and replace encoders has been proposed. It is shown that this idea can be employed in AUT scanner without encoders. That is, one transducer transmitting surface wave is fixed and the other transducer attached to the scanner receives UT signal. Then, computer calculates the present position of scanner based on the information given by surface wave. Thus, the movement of a scanner can be controlled by the amount of input based on the information obtained.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• 제25권2호
• /
• pp.193-201
• /
• 2021

The welding has a high proportion of the production and drying of ships or offshore plants. Non-destructive testing is carried out to verify the quality of welds in Korea, radiography test (RT) is mainly used. Currently, most shipyards adopt analog-type techniques to print the films through the shoot of welding parts. Therefore, the time required from radiography test to pass or fail judgment is long and complex, and is being manually carried out by qualified inspectors. To improve this problem, this paper covers a platform for scanning and digitalizing RT films occurring in shipyards with high resolution, accumulating them in management servers, and applying artificial intelligence (AI) technology to detect welding defects. To do this, we describe the process of designing and developing RT film scanning equipment, welding inspection information integrated management platform, fault reading algorithms, visualization software, and testing and verification of each developed element in conjunction.

• Journal of the Korea Society of Computer and Information
• /
• 제25권3호
• /
• pp.19-26
• /
• 2020

Steel production requires high-quality surfaces with minimal defects. Therefore, the detection algorithms for the surface defects of steel strip should have good generalization performance. To meet the growing demand for high-quality products, the use of intelligent visual inspection systems is becoming essential in production lines. In this paper, we proposed a ShuffleDefectNet defect detection system based on deep learning. The proposed defect detection system exceeds state-of-the-art performance for defect detection on the Northeastern University (NEU) dataset obtaining a mean average accuracy of 99.75%. We train the best performing detection with different amounts of training data and observe the performance of detection. We notice that accuracy and speed improve significantly when use the overall architecture of ShuffleDefectNet.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• 제44권10호
• /
• pp.862-870
• /
• 2016

AIS and V-PASS, which are used for safe navigation and automatic vessel arrival and departure, are mandatory standard equipment installed on all ships. If an aircraft is equipped with a ship identification system using AIS and V-PASS, and then ship identification information is received by a vessel such as a large fishery inspection boat or a patrol ship or a ground control system, we can quickly perform maritime surveillance and disaster response. This paper describes the development of a ship identification and display system using a ship identification device for aircraft. Flight test results and a future application plan are also included.

• Transactions of the Korean Society of Pressure Vessels and Piping
• /
• 제6권1호
• /
• pp.78-82
• /
• 2010

The feeder pipe of Main Primary Heat Transfer System in Wolsong Nuclear Power Plant was inspected by the Ultrasonic Phase Array technique in 2010. It is the first time to apply this method to the construction at Nuclear Power Plant in Korea. The time required for UT technique is less than RT method. The UT method doesn't need to evacuate personnel who works nearby inspecting area and doesn't need to wait developing of film. For these reasons, the UT method is the fastest method among the volumetric inspections. As a result of the examination, it became clear that main defect of the feeder pipe is the Lack of fusion in the welded area. Moreover, the rate of defect was reduced gradually as improvement of welder's skill. If welding machine has problem, the defect has tended to same pattern(occurred same position in the welding area) but these defects were founded without specific rules. For these reasons, the creation of defect is dependent on the skill of worker not on the automatic welding machine. This evaluation of defect signal and collecting data would be useful to further examination in ISI.

• Proceedings of the KIEE Conference
• /
• 대한전기학회 1991년도 하계학술대회 논문집
• /
• pp.47-50
• /
• 1991

LPM(Linear Pulse Motor) provide direct and precise position control of bidirectional linear motion. LPM is not subject to the same linear velocity and acceleration limitations inherent in systems converting rotary to linear motion such as lead screws, rack and pinion, belt and pulley drives. With LPM, all the thrust force generated by the motor is efficiently applied directly to the load. And speed, distance, and acceleration are easily programmed in a highly repeatable fashion. Potential industrial and application fields of LPM include PCB assembly, industrial sewing machines, automatic inspection, coil winder, medical uses, conveyer system, laser cut and trim systems, semiconductor wafer processing, OA instruments etc. This paper describes various design parameter of LPM such as magnetic ciucuit construction methods, phase number and tooth number per pole, permanent magnet and coil mmf, tooth geometries. And to solve the problems of existing control methods, in this paper, a new control method of the LPM is proposed throughout modern control theory.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• 제17권9호
• /
• pp.2145-2152
• /
• 2013

Paper manufacturing industries have huge facilities with automatic equipments. Especially, in order to improve the efficiency of the paper manufacturing processes, it is necessary to detect the paper cutting defect effectively and to classify the causes correctly. In this paper, we review the problems of web monitoring system and web inspection system that have been traditionally used in industries for defect detection. Then we propose a novel paper cutting defect detection method based on the local binary pattern analysis and its implementation to mitigate the practical problems in industry environment. The proposed algorithm classifies the defects into edge-type and region-type and then it is shown that the proposed system works stably on the real paper cutting defect detection system.