• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.27-35
• /
• 2023

In this paper, we propose a process of increasing productivity by applying a deep learning-based defect detection and classification system to the prepreg fiber manufacturing process, which is in high demand in the field of producing composite materials. In order to apply it to toe prepreg manufacturing equipment that requires a solution due to the occurrence of a large amount of defects in various conditions, the optimal environment was first established by selecting cameras and lights necessary for defect detection and classification model production. In addition, data necessary for the production of multiple classification models were collected and labeled according to normal and defective conditions. The multi-classification model is made based on CNN and applies pre-learning models such as VGGNet, MobileNet, ResNet, etc. to compare performance and identify improvement directions with accuracy and loss graphs. Data augmentation and dropout techniques were applied to identify and improve overfitting problems as major problems. In order to evaluate the performance of the model, a performance evaluation was conducted using the confusion matrix as a performance indicator, and the performance of more than 99% was confirmed. In addition, it checks the classification results for images acquired in real time by applying them to the actual process to check whether the discrimination values are accurately derived.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.14 no.4
• /
• pp.264-272
• /
• 2011

Shipbuilders carry out the operation test to check the conditions of the main propulsion system and auxiliaries for moored vessel in the quoy before the sea trial. The estimation of the thrust and torque for the partially submerged propeller should be prepared to ensure the safety of mooring line and the ship. In this paper, the variations of the thrust and torque according to the shaft submergence and the propeller rotating speed in bollard pull condition are investigated with the model test and the numerical analysis. Based on these resaearch, the empirical formula representing the physical phenomena of the partially submerged propeller is derived and validated through comparison to measurement results of full-scale propellers under the quoy operation test.

• Journal of Energy Engineering
• /
• v.23 no.3
• /
• pp.116-124
• /
• 2014

In the plants operated under high temperature condition, piping system load analysis is often performed to prevent accidents caused by thermal deformation and also to locate inspection prioritity points of the piping system. In this study, piping system stress analysis was performed for a pipe system between the reactors in a process plant. The piping system includes typically installed hangers and expansion joints. In order to evaluate the effects of structural components such as hangers and expansion joints, the case for the expansion joint or the hanger under abnormal operation is considered. By comparison anlaysis results of piping system during normal operation and abnormal operation, the role of each pipe components are studied.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2017.04a
• /
• pp.149-149
• /
• 2017

본 논문은 생산라인 자동화를 위한 로봇으로 제조업 시장 확대에 가장 큰 걸림돌이 되는 가격 경쟁력 및 인력난 해소를 위해 설계하였으며 다양한 소재에 대응하기 위해 그리퍼를 교체하여 적용이 되도록 하였다. 자동화를 위한 로봇은 소재의 내외경 가공 및 검사까지 모든 공정이 일괄적으로 이루어 져야하며 LCD 모니터에 생산수량 및 불량률 등의 정보를 실시간으로 나타내어 효율적인 생산계획을 수립할 수 있도록 하였다. 생산라인 자동화를 위해 로봇의 설계는 Auto CAD를 이용하였다. 부품의 가공은 CNC에 적용하기 위해 자동공급장치를 설계하였다. 가공이 완료된 후 측정한 값을 LCD모니터를 통하여 작업자가 알아볼 수 있게 나타냈다. 외경 1은 40.405, 외경2는 32.201, 내경 1은 23.346, 내경 2는 34.302로 나타났다. 측정결과 불량 측정을 위해 측정부의 결과 값이 나타나며 불량이 발생하면 그래프를 이용하여 어떤 부위에서 발생했는지를 알 수 있도록 하였다. 또한 결과 값은 자동으로 저장되도록 하였다. 생산라인 자동화를 위해 100EA를 측정한 결과 외경 1은 40.40438, 외경2는 32.20164, 내경 1은 23.34830 내경 2는 34.30033의 평균값을 나타냈다. 측정값의 검증은 하이트게이지로 측정한 결과 0.003 이내의 결과를 나타냈다. 따라서 본 로봇 자동화 시스템을 적용한다면 생산성 향상 및 불량률 감소가 가능하여 인력대체 및 가격경쟁력이 가능하다고 판단된다.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.34 no.1
• /
• pp.73-76
• /
• 2010

The issue of inspection and characterization of microstructures has emerged as a major consideration in design, fabrication, and detection of MEMS devices. However, the conventional measurement techniques, including scanning electron microscopy (SEM) imaging, atomic force microscopy (AFM) scanning, and mechanical surface profiler, require often destructive process or may be difficult to measure with a wafer scale. In this paper, we characterize the surface profiles of microstructures using an optical scanner based on a DVD pick-up module. Scanning images of the microstructures are successfully generated using the intensity of reflected light from different depths of the surface profiles, based on the focus error signal (FES) from photodiodes. It is shown that the proposed optical scanner can be used as an alternative measurement system with high performance and low cost, compared to conventional measurement techniques.

• Journal of Energy Engineering
• /
• v.18 no.1
• /
• pp.63-68
• /
• 2009

The safety culture of an organization is very complex and hard to study, but it is possible to examine norms that make up the culture. This paper describes of a Process Safety Management (PSM) climate assessment tool developed in high risk industry such as chemical industries. The main purpose is to develop measuring software tool behaviors by examining their nature and strength and by analysing underlying factors that offer explanations for attitudinal differences. We reviewed the current techniques and literatures available to assess safety climate and culture, conducted focus group interviews and discussions. Based on the reviews and focus group, PSM climate assessment questionnaires and an online application program were developed. A pilot assessment was done at a chemical plant in Korea and the safety climate profile was completed. It was suggested to have a constant feedback from different sectors of industry to improve the application.

• Korean Journal of Food Science and Technology
• /
• v.23 no.6
• /
• pp.723-731
• /
• 1991

In order to optimize sterilization conditions of retort pouched curry sauce, sterilization processes for eighteen conditions by varying temperature, time and method were conducted through $3^{2}{\times}2^{1}$ experimental factorial design. Quality evaluations before and after sterilization included measurements of vitamin (niacin) retention, pH and color differences, and organoleptic test(taste, color and viscosity). $F_{o}$ values were also measured at each condition. Product qualities were mainly affected by sterilization temperature and time, whereas sterilization method had no significant effect. Effect of sterilization time on product qualities was higher than that of sterilization temperature. From the response surface analysis, an optimum range of sterilization condition simultaneously satisfying desired specifications was determined to be $123.5^{\circ}C$, 21.5 min to $127.5^{\circ}C$, 17.0 min. In this range, the sterility($F_{o}$ value) at a cold point during sterilization was approximately 15.0 min.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.30 no.2
• /
• pp.264-270
• /
• 1997

To obtain basic data for processing semi-dried salmon meat product, the results that were measured the textural properties of salmon meat during salting, sugaring and drying process followed. Drying time and temperature were longer, the moisture amount of salmon meat were reduced. Hardness of salmon meat was direct proportion to shear stress, but hardness was inverse proportion to cohesiveness during drying process. After sugaring and salting salmon meat, drying time was longer, hardness and shear stress of salmon meat were increased. The sensory evaluation of the textures of sugaring salmon meat dried for 3 hrs showed slightly good. In the changes of texture of salmon meat during steaming hardness and shear stress of salmon meat dried for 4 hrs were higher than that dried for 10 hrs. And steaming time was longer, hardness of salmon meat dried for 4 hrs was decreased and cohesiveness was not changed.

• Journal of Advanced Navigation Technology
• /
• v.13 no.2
• /
• pp.238-243
• /
• 2009

Now, the production process systems are largely based on automatic system using the wired network. The production process systems using wired network has disadvantage that it is expensive when the installed and replaced equipment. The each equipment happens to repair cost for control and management in production processes. And the replaced equipment has also the additional expense and breaks production process. These problems are solved through wireless communication between the industrial equipments. So, we propose wireless production process system based on IEEE 802.15.4 technology. It solves a complicated space and stops by replaced equipment in the factory. Then we simulated and analyzed IEEE 802.15.4 for Industrial Equipment based on Wireless Network.

• Proceedings of the KAIS Fall Conference
• /
• 2010.11b
• /
• pp.1017-1020
• /
• 2010

최근 국산 농산물의 수요급증과 더불어 소비자들은 안전한 제품의 요구가 높아지고 있다. 이러한 요구에 맞는 제품 개발의 일환으로 미생물 제어가 된 고춧가루 포장제품의 품질향상을 위한 천연항균 물질 소재를 탐색하여 제품개발에 응용하였다. 천연물과 한방재료 중 고춧가루 제품에 적합한 소재를 스크리닝하여 항균물질을 탐색하였으며 고춧가루 제품 패킹에 응용하였다. 천연물 항균제의 개발 원칙은 산취 등 이취가 없어야 하며, 제품에 응용할 수 있는 용해성이나 믹싱의 효과를 높이도록 공정을 최적화 하였다. 또한 최종 천연물 항균제의 형태는 분말 형태로 개발하였다. 천연물에 대한 항균활성은 paper disk test를 통하여 비교하였으며, 항균력이 가장 우수한 소재는 황금추출물이었다. 또한 이들 추출물과 비타민 $B_1$ 인산염의 영향을 함께 비교하였다. 이 천연물 소재 추출물로 개발한 항균물질에 대한 효과는 일반세균, 대장균 검사를 실시하였다. 제품의 안정성 확보 및 유통기한 연장 가능성을 실험한 결과, 일반세균은 $1.0{\times}10^5$cfu/g, 대장균군은 $1.0{\times}10^2$cfu/g, 대장균은 불검출 되었다. 이들 추출물의 항균제 개발과 더불어 다양한 식품에 천연물 항균제로서의 적용 가능성을 모색하고자 하며, 안전한 천연 항균제 개발에 대한 기초 자료를 제공하는 기초 연구를 하고자 하였다.