• Fire Science and Engineering
• /
• v.9 no.1
• /
• pp.3-9
• /
• 1995

This paper is a study to dectect the tracking owing to deterioration of indoor wiring, and to prevent the electrical fire. After analysing the harmonics of waveshapes in load current and tracking current by FFT, a method of identifying the tracking was developed by using neural network. Fluoscent lamp, witch was mostly used in indoor, was chosen as the load used in this study. When the learning number in neural network was more then 30,000 times, an excellent neural net-work which could correctly identify the tracking was established. Therefore, the result of this study can be utilized as a basic material in various measuring instruments, such as an hotline inslation tester, earth tester in vehicles, and tracking fire alarm device, witch can detect the tracking under the condition of hotline.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.61-61
• /
• 2000

Since FMS(Flexible Manufacturing System) such as semiconductor production systems have the characteristic that each device has to be commonly used in several stages, it is difficult to find an optimal solution. In this paper, we proposed the new algorithm which can get the optimal ratio of sharing resources. We will implement the proposed algorithm to semiconductor production systems. We introduce the optimal algorithm, which is modeled and analyzed by ExSpect, a petri net based simulation tool. When there exist conflicts of sharing resources, the scheduling method is adopted, which gives a priority to the most preceded process. The suggested algorithm can be used not only in semiconductor production systems but also in various FMS.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.3
• /
• pp.490-493
• /
• 2021

This paper proposes an embedded system that detects mask and face recognition based on a microprocessor instead of Nvidia Jetson Board what is popular development kit. We use a class of efficient models called Mobilenets for mobile and embedded vision applications. MobileNets are based on a streamlined architechture that uses depthwise separable convolutions to build light weight deep neural networks. The device used a Maix development board with CNN hardware acceleration function, and the training model used MobileNet_V2 based SSD(Single Shot Multibox Detector) optimized for mobile devices. To make training model, 7553 face data from Kaggle are used. As a result of test dataset, the AUC (Area Under The Curve) value is as high as 0.98.

• Journal of Information Technology Applications and Management
• /
• v.26 no.6
• /
• pp.103-117
• /
• 2019

Demand for high power motors is rapidly increasing as the 4th industry and convergence technology has recently emerged. In order to produce high-strength permanent magnets, the magnets used for magnetization have been increased from DC 300V in the 1970s to DC 2.5kV in the 2010s, Up to DC 10kV in the 2030s, It is expected that higher voltage will be used to magnetize. However, in the case of a magnetizer using an existing electric signal control device, it is necessary to use a control device with a high-voltage insulation function in case a high voltage used for magnetization is leaked to the control device. If a short circuit accident occurs, the controller must be shut down and serious problems such as excessive repair costs arise. In this study, a control system adopting optical communication method instead of electric signal control method is proposed to prevent leakage currents in high-voltage magnetizer. We design a transmitter(Tx) and a receiver(Rx) device for the optical communication control device and implemented a prototype connecting the optical cable. In order to demonstrate the utility of high-voltage magnetizer using the optical communication control device, we analyzed the initial cost and the yearly cost for the years to analyze the net present value. As a result, In the case of the low-voltage magnetizer, the electric signal control method cost less, As the operating voltage of the magnetizer becomes higher. It is confirmed that it takes less cost when the optical communication control device is used.

• Korean Chemical Engineering Research
• /
• v.55 no.6
• /
• pp.816-821
• /
• 2017

An integrated slow mixing/sedimentation and net fit fiber filtration system has been developed to reduce the high concentrations of suspended solid (SS) and total phosphorus (T-P) in the reject water from sewage/wastewater. A filtration device used in this experiment consists of coagulation, in-line mixing, air injection, slow mixing/sedimentation, and filtration processes. The performance test using this device was carried out with six operational modes for reject water from sewage treatment plant. Experimental conditions used were 16.7, 33.3, 41.7 and 50.0 ton/day of flow rate and 2~4 of Al/P molar ratio. By injection of coagulant in each operational mode, the high removal efficiencies of SS and T-P were obtained, but continuous operation time was decreased to 7.8~11.4 min in most modes. However, when the Mode 5 of the developed filtration device was applied, the continuous operation time was maintained up to 88.2 min. Also, it was found that the continuous operation time in the Mode 5 using the developed system was increased from 8 to 11.3 times longer than those in other modes. Backwashing flow rate was also very low at 5.4% of total filtered water. Therefore, it can be concluded that the Mode 5 of the developed filtration system was the most efficient treatment method for the removal of high concentrations of SS and T-P.

• Journal of Aerospace System Engineering
• /
• v.11 no.5
• /
• pp.36-41
• /
• 2017

As the space debris in the satellite orbit increases, the risk of collision between the currently operating satellites and the space debris is continuously increasing. Therefore, in this study, we designed one-degree-of-freedom capture device using simple deployment mechanism. The capture device consists of four link groups connected with net. To increase the reliability, each link group is connected to one driving part so that the total degree of freedom is 1. In addition, the links were stowed on each side of the satellites so that they would not affect the janitor satellite mission. Finally, to confirm the possibility of deployment in the space environment, we carried out deployment experiments in water similar to the microgravity environment, and confirmed the deployment of capture device and the possibility of capturing target satellite.

• Journal of Biomedical Engineering Research
• /
• v.42 no.4
• /
• pp.150-158
• /
• 2021

Intracranial hemorrhage (ICH) refers to acute bleeding inside the intracranial vault. Not only does this devastating disease record a very high mortality rate, but it can also cause serious chronic impairment of sensory, motor, and cognitive functions. Therefore, a prompt and professional diagnosis of the disease is highly critical. Noninvasive brain imaging data are essential for clinicians to efficiently diagnose the locus of brain lesion, volume of bleeding, and subsequent cortical damage, and to take clinical interventions. In particular, computed tomography (CT) images are used most often for the diagnosis of ICH. In order to diagnose ICH through CT images, not only medical specialists with a sufficient number of diagnosis experiences are required, but even when this condition is met, there are many cases where bleeding cannot be successfully detected due to factors such as low signal ratio and artifacts of the image itself. In addition, discrepancies between interpretations or even misinterpretations might exist causing critical clinical consequences. To resolve these clinical problems, we developed a diagnostic model predicting intracranial bleeding and its subtypes (intraparenchymal, intraventricular, subarachnoid, subdural, and epidural) by applying deep learning algorithms to CT images. We also constructed a visualization tool highlighting important regions in a CT image for predicting ICH. Specifically, 1) 27,758 CT brain images from RSNA were pre-processed to minimize the computational load. 2) Three different CNN-based models (ResNet, EfficientNet-B2, and EfficientNet-B7) were trained based on a training image data set. 3) Diagnosis performance of each of the three models was evaluated based on an independent test image data set: As a result of the model comparison, EfficientNet-B7's performance (classification accuracy = 91%) was a way greater than the other models. 4) Finally, based on the result of EfficientNet-B7, we visualized the lesions of internal bleeding using the Grad-CAM. Our research suggests that artificial intelligence-based diagnostic systems can help diagnose and treat brain diseases resolving various problems in clinical situations.

• Nuclear Engineering and Technology
• /
• v.45 no.7
• /
• pp.941-950
• /
• 2013

The Korean Nuclear-Hydrogen Technology Development (NHTD) Plan will be performing irradiation testing of coated particle fuel at HANARO to support the development of VHTR in Korea. This testing will be carried out to demonstrate and qualify TRISO-coated particle fuel for use in VHTR. The testing will be irradiated in an inert gas atmosphere without on-line temperature monitoring and control combined with on-line fission product monitoring of the sweep gas. The irradiation device contains two test rods, one has nine fuel compacts and the other five compacts and eight graphite specimens. Each compact contains about 260 TRISO-coated particles. The irradiation device is being loaded and irradiated into the OR5 hole of the in HANARO core from August 2013. The device will be operated for about 150 effective full-power days at a peak temperature of about $1030^{\circ}C$ in BOC (Beginning of Cycle) during irradiation testing. After a peak burn-up of about 4 atomic percentage and a peak fast neutron fluence of about $1.7{\times}10^{21}\;n/cm^2$, PIE (Post-Irradiation Examination) of the irradiated coated particle fuel will be performed at IMEF (Irradiated Material Examination Facility). This paper reviews the design of test rod and irradiation device for coated particle fuel, and discusses the technical results for irradiation testing at HANARO.

• Journal of Korea Multimedia Society
• /
• v.18 no.5
• /
• pp.631-640
• /
• 2015

Recently CCTV system is installed widely purpose to enhanced physical security, gathering criminal evidence and management of facilities. In spite of supporting strong management function, CCTV system has weak security function. Therefore high security management function is required. Generally it's not easy to control the devices under NAT using a NMS(Network Management System). So we design and implement alive check algorithm of CCTV devices under NAT using DVRNS address resolution and TCP session check. We evaluated and analyzed of developed system on real environment which includes about 100 DVRs under NAT. As a result of test, it showed that device alive check and DVRNS address resolution were well performed without any error.

• Journal of the Korean Vacuum Society
• /
• v.8 no.4B
• /
• pp.556-564
• /
• 1999

The analysis on heat fluxed on and transmission efficiencies by the collimators of neutral beam injection lines in KSTAR tokamak device has been carried out. And a mathematical model describing non-Gaussian beam distribution profile has been established. A neutral beam injection device is composed of 3 separate ion sources and corresponding beam transport lines, which deal with 7.8 MW of beam power, respectively. The divergence angles of ion beam are $1.2^{\circ}$and $0.5^{\circ}$, in vertical and horizontal directions, respectively. The maximum normal heat load on source exit scraper is 9.1 kW/$\textrm{cm}^2$ and net beam transmission efficiency is ~28%. The effect of misalignment of ion source and scrapers on the scraper heat load and beam transmission also has been analyzed.