• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.262-264
• /
• 2016

In order to check the status of tire wear, a driver or auto mechanic generally checks tires with the naked eyes or with a coin. Those are easy for anyone but make it difficult to obtain precise information. But the result is a measure of mechanic wear out due to subjective judgment. Since we can not give correctly measure the stability of the tire. This may lead to an accident of the operator. Therefore, there is a need for a system checking tires precisely, accurately and easily, while making up for the aforementioned defect. This thesis has implemented a system with the aforementioned function. This system tire surface scanner data unit to determine the tread wear on the car and a storage unit for the data save, And a Web service unit allows the user to easily check the information.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.2_1
• /
• pp.177-184
• /
• 2022

The automatic defect sorting function of machinery parts is being introduced to the automation of the manufacturing process. In the final stage of automation of the manufacturing process, it is necessary to apply computer vision rather than human visual judgment to determine whether there is a defect. In this paper, we introduce a deep learning method to improve the classification performance of typical mechanical parts, such as welding parts, galvanized round plugs, and electro galvanized nuts, based on the results of experiments. In the case of poor welding, the method to further increase the depth of layer of the basic deep learning model was effective, and in the case of a circular plug, the surrounding data outside the defective target area affected it, so it could be solved through an appropriate pre-processing technique. Finally, in the case of a nut plated with zinc, since it receives data from multiple cameras due to its three-dimensional structure, it is greatly affected by lighting and has a problem in that it also affects the background image. To solve this problem, methods such as two-dimensional connectivity were applied in the object segmentation preprocessing process. Although the experiments suggested that the proposed methods are effective, most of the provided good/defective images data sets are relatively small, which may cause a learning balance problem of the deep learning model, so we plan to secure more data in the future.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.26 no.8
• /
• pp.79-87
• /
• 2012

Currently, The method to produce a brewing body for dentistry supplementation water produces a brewing body by fabrication, burying and it is heat wish in city gas and oxygen. It uses an original judgment found airplane the brewing body uses a spring of the back wait that melting temperature dissolved various alloys in by a blow pipe, and to generate centrifugal force and produces it. In addition, because it uses preheating to dissolve an alloy in general, it is hard to regulate the appropriate melting temperature of the alloy and brewing time and generates a brewing defect hereby same as gas industry and pinhole and shows the defect of the supplementation thing due to the super-heating. In this paper, We developed the high induction heating system which it could set brewing time,temperature and had durability and security,by the kind of the alloy to produce a high quality prosthetic thing brewing body.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.1
• /
• pp.107-116
• /
• 2024

Copper Filter Dryer (CFD) are responsible for removing impurities from the circulation of refrigerant in refrigeration and cooling systems to maintain clean refrigerant, and defects in CFD can lead to product defects such as leakage and reduced lifespan in refrigeration and cooling systems, making quality assurance essential. In the quality inspection stage, human inspection and defect judgment methods are traditionally used, but these methods are subjective and inaccurate. In this paper, YOLOv7 object detection algorithm was used to detect defects occurring during the CFD Shaft pipe and welding process to replace the existing quality inspection, and the detection performance of F1-Score 0.954 and 0.895 was confirmed. In addition, the cause of defects occurring during the welding process was analyzed by analyzing the sensor data corresponding to the Timestamp of the defect image. This paper proposes a method for manufacturing quality assurance and improvement by detecting defects that occur during CFD process and analyzing their causes.

• Korean Security Journal
• /
• no.10
• /
• pp.293-322
• /
• 2005

The culpability of a person, as determined by due process of law, for any of his actions that are defined as criminal. Determination of such responsibility is a legal function, not a psychiatric one, although a psychiatrist may be called upon to present evidence to the court in order to aid the judge or jury in reaching a decision as to responsibility. Determination of responsibility varies with the laws of the state in which the accused is being tried, but in general all states base their laws on three famous judicial decisions concerning criminal responsibility. 1. the M'Naghten(McNaughton) rule(a. to establish such a defense the accused, at the time the act was committed, must be shown to have been laboring under such defect of reason as not to know the nature and quality of the act he was doing, b. if he did know it, he did or know that what he was doing was wrong). 2. the irresistible impulse test. 3. the Durham decision. Under the Durham test, however, the psychiatrist may give any relevant testmony concerning the mental illness at issue. The psychological and behavioral appearance of a person, in clinical psychiatry this term is commonly used to refer to the results of the mental examination of a patient. The written report of the mental status usually contains specific references to the following areas: I. Attitude and General Behavior (1)General health and appearance. (2)General habits of dress. (3)Personal habits. (4)General mood. (5)Use of leisure time. (6)Degree of sociability. (7)Speech. II. Attitude and Behavior during interview (1)Co-operativeness. (2)Poise. (3)Facial expression. (4)Motor activity. (5)Mental activity. (6)Emotional reactions. (7)Trend of thought. III. Sensorium, mental grasp, and capacity (1)Orientation. (2)Memory and retention. (3)Estimate of intelligence. (4)Abstraction ability. (5)Tests of absurdity, interpretation of proverbs. (6)Judgment.

• Journal of the Korea Institute of Building Construction
• /
• v.21 no.2
• /
• pp.129-139
• /
• 2021

Recent rise in the supply rate of new public apartment houses leads to an increasement in disputes regarding the construction quality of the apartments between the residents and the construction companies. According to the dispute cases filed for claiming the collective defect repair fees, inter-layer concrete joints turned out to be the most frequently disputed item. For this reason, this study selects the inter-layer concrete joints to further analyze the primary causes and details of each dispute case. From the results of this study, three primary causes of the disputes are found, which are 1) the absence of standard specifications for construction quality control and management after construction; 2) the absence of established standards for repair when construction defects are found; and 3) the fact that the court grants generous compensation for disputes concerning the apartment houses. In order to prevent construction defects in inter-layer concrete joints, this study provides three suggestions including 1) the current standard specifications for inter-layer concrete joints should be further specified by the Ministry of Land, Infrastructure and Transport; 2) a construction defect should be judged according to the compliance to the standard specifications; and 3) a clear and institutional protocol needs to be established for defect repair in cases that new public apartment houses have been judged to have defects.

• Journal of the Korea Convergence Society
• /
• v.8 no.11
• /
• pp.43-48
• /
• 2017

Semiconductors are leading the development of industrial technology, leading to miniaturization and weight reduction of electronic products as a leading technology, we are dragging the electronic industry market Especially, the semiconductor manufacturing process is composed of highly accurate and complicated processes, and effective production is required Recently, a vision system combining a computer and a camera is utilized for defect detection In addition, the demand for a system for measuring the shape of a fine pattern processed by a special process is rapidly increasing. In this paper, we propose a vision algorithm using mask image to detect scratch defect of semiconductor pockage. When applied to the manufacturing process of semiconductor packages via the proposed system, it is expected that production management can be facilitated, and efficiency of production will be enhanced by failure judgment of high-speed packages.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.2
• /
• pp.505-510
• /
• 2024

Since rolling contact fatigue cracks can always occur on the rail surface, which is the contact surface between wheels and rails, railway rails require thorough inspection and diagnosis to thoroughly inspect the condition of the cracks and prevent breakage. Recent detailed guidelines on the performance evaluation of track facilities present the requirements for methods and procedures for track performance evaluation. However, diagnosing and grading rail surface damage mainly relies on external inspection (visual inspection), which inevitably relies on qualitative evaluation based on the subjective judgment of the inspector. Therefore, in this study, we conducted a deep learning model study for rail surface defect detection using Fast R-CNN. After building a dataset of rail surface defect images, the model was tested. The performance evaluation results of the deep learning model showed that mAP was 94.9%. Because Fast R-CNN has a high crack detection effect, it is believed that using this model can efficiently identify rail surface defects.

• The Korean Journal of Air & Space Law and Policy
• /
• v.30 no.1
• /
• pp.151-180
• /
• 2015

South Korea is advancing the unmanned aircraft private commercial business. Unmanned aerial vehciles industry has been developing for several years also abroad. However, unmanned aerial vehciles industry, can be an accident occurs. Accident of unmanned aerial vehciles to occur material damage and casualties. Particularly if an accident because of a defect in the unmanned aerial vehciles has occurred, it is necessary to analyze the liability for this. The defect accidents unmanned aerial vehciles has been the different manufacturing and design product is intended, whether it is important how to prove to this. This is because, unmanned aerial vehciles are designed in any intent of the original, it is impossible to victims know. So imposing a responsibility to prove the design by the manufacturer intended consumer is not fair. Moreover, the consumer, it is necessary to prove only that the product is one that normally dangerous lacked safety can be expected. This is a detailed issue of judgment of defects of unmanned aerial vehciles, the manufacturer to bear the accountability. In the case where the defect on the display of the unmanned aircraft is a problem, and if it reasonable indication, it is not appropriate to be required to prove that it was possible to prevent damage to the victim.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.6
• /
• pp.1274-1279
• /
• 2011

The purpose of this paper is to present the manufacturing defect and damage pattern of a 3 phase 22.9/3.3kV oil immersed transformer, as well as to present an objective basis for the prevention of a similar accident and to secure data for the settlement of PL related disputes. It was found that in order to prevent the occurrence of accidents to transformers, insulating oil analysis, thermal image measurement, and corona discharge diagnosis, etc., were performed by establishing relevant regulation. The result of analysis performed on the external appearance of a transformer to which an accident occurred, the internal insulation resistance and protection system, etc., showed that most of the analysis items were judged to be acceptable. However, it was found that the insulation characteristics between the primary winding and the enclosure, those between the ground and the secondary winding, and those between the primary and secondary windings were inappropriate due to an insulating oil leak caused by damage to the pressure relief valve. From the analysis of the acidity values measured over the past 5 years, it is thought that an increase in carbon dioxide (CO2) caused an increase in the temperature inside the transformer and the increase in the ethylene gas increased the possibility of ignition. Even though 17 years have passed since the transformer was installed, it was found that the system's design, manufacture, maintenance and management have been performed well and the insulating paper was in good condition, and that there was no trace of public access or vandalism. However, in the case of transformers to which accidents have occurred, a melted area between the upper and the intermediate bobbins of the W-phase secondary winding as well as between its intermediate and lower bobbins. It can be seen that a V-pattern was formed at the carbonized area of the transformer and that the depth of the carbonization is deeper at the upper side than the lower side. In addition, it was found that physical bending and deformation occurred inside the secondary winding due to non-uniform pressure while performing transformer winding work. Therefore, since it is obvious that the accident occurred due to a manufacturing defect (winding work defect), it is thought that the manufacturer of the transformer is responsible for the accident and that it is lawful for the manufacture to investigate and prove the concrete cause of the accident according to the Product Liability Law (PLL).