• 한국원자력학회:학술대회논문집
• /
• 한국원자력학회 1995년도 추계학술발표회논문집(1)
• /
• pp.153-158
• /
• 1995

All of the nuclear power plants in Korea we operating with analog instrumentation and control (I&C) equipment which are increasingly faced with frequent troubles, obsolescence and high maintenance expenses. Electrical and computer technology has improved rapidly in recent years and has been applied to other industries. So it is strongly recommended we adopt modern digital and computer technology to improve plant safety and availability. The advanced I&C system, namely, Integrated Intelligent Instrumentation and Control System (I$^3$CS) will be developed for beyond the next generation nuclear power plant. I$^3$CS consists of three major parts, the advanced compact workstation, distributed digital control and protection system including Automatic Start-up/shutdown Intelligent Control System (ASICS) and the computer-based alarm processing and operator support system, namely, Diagnosis, Response, and operator Aid Management System (DREAMS).

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1996년도 추계학술대회 논문집
• /
• pp.212-216
• /
• 1996

Recently, with the development of NC and CNC machine tools and the high labor wage, the cutting process requires the high speed and automatic system which uses industrial robots and the flexible manufacturing system(FMS) that combines several machine tools. In this system, the whole system can be influenced by just one of the machin tools. So it needs to detect a problem and to solve it immediately In in-process state. The monitoring system through measuring the motor current with current sensor has been attracting the attention of lots of researchers view of its low cost and flexibility. By using the pattern discriminant with the detected three-phase-current signal, that is, $I_{RMS}$, a system which can monitor and analyze abnormal machining process condition of the workpiece during the machining will be able to be developed in this research.h.

• Journal of Electrical Engineering and Technology
• /
• 제11권4호
• /
• pp.993-1002
• /
• 2016

Hepatitis is a major public health problem all around the world. This paper proposes an automatic disease diagnosis system for hepatitis based on Genetic Algorithm (GA) Wavelet Kernel (WK) Extreme Learning Machines (ELM). The classifier used in this paper is single layer neural network (SLNN) and it is trained by ELM learning method. The hepatitis disease datasets are obtained from UCI machine learning database. In Wavelet Kernel Extreme Learning Machine (WK-ELM) structure, there are three adjustable parameters of wavelet kernel. These parameters and the numbers of hidden neurons play a major role in the performance of ELM. Therefore, values of these parameters and numbers of hidden neurons should be tuned carefully based on the solved problem. In this study, the optimum values of these parameters and the numbers of hidden neurons of ELM were obtained by using Genetic Algorithm (GA). The performance of proposed GA-WK-ELM method is evaluated using statical methods such as classification accuracy, sensitivity and specivity analysis and ROC curves. The results of the proposed GA-WK-ELM method are compared with the results of the previous hepatitis disease studies using same database as well as different database. When previous studies are investigated, it is clearly seen that the high classification accuracies have been obtained in case of reducing the feature vector to low dimension. However, proposed GA-WK-ELM method gives satisfactory results without reducing the feature vector. The calculated highest classification accuracy of proposed GA-WK-ELM method is found as 96.642 %.

• 반도체디스플레이기술학회지
• /
• 제10권3호
• /
• pp.95-98
• /
• 2011

System to urinalysis using FT-IR instruments is presented based on fuzzy logic knowledge. Linguistic expressions of the possibility of infection and the importance were quantified and membership functions were determined based on general quantitative criteria. Diseases considered were Diabetes Mellitus, Proteinuria, Microalbuminuria. Glucose, Protein, Albumin, Creatinine in 30 samples were analyzed by the present system, which resulted in 74% accuracy. The simple mathematical formulation of present system would enable an easy implementation in commercial analysis instruments. Also, the identical fuzzy logic can be applied to similar diagnostic environments in general.

• KEPCO Journal on Electric Power and Energy
• /
• 제8권2호
• /
• pp.119-126
• /
• 2022

A growing number of gas-insulated transformers in underground power substations in urban areas are approaching 20 years of operation, the time when failures begin to occur. It is thus essential to prevent failure through accurate condition diagnosis of the given facility. Various solid insulation materials exist inside of the transformers, and the generated decomposition gas may differ for each gas-insulated equipment. In this study, a simulation system was designed to analyze the deterioration characteristics of SF₆ decomposition gas and insulation materials under the conditions of partial discharge and thermal fault for diagnosis of gas-insulated transformers. Degradation characteristics of the insulation materials was determined using an automatic viscometer and FT-IR. The analysis results showed that the pattern of decomposition gas generation under partial discharge and thermal fault was different. In particular, acetaldehyde was detected under a thermal fault in all types of insulation, but not under partial discharge or an arc condition. In addition, in the case of insulation materials, deterioration of the insulation itself rapidly progressed as the experimental temperature increased. It was confirmed that it was possible to diagnose the internal discharge or thermal fault occurrence of the transformer through the ratio and type of decomposition gas generated in the gas-insulated transformer.

• 한국전자통신학회논문지
• /
• 제18권1호
• /
• pp.53-62
• /
• 2023

최근 신재생에너지 증가로 인하여 가스터빈 발전기는 양질의 전력공급을 위해 일일 기동·정지가 지속되고 있으며 이에 따른 영향으로 고온부품의 수명이 단축되고 고온 측정용 온도센서의 고장발생 빈도가 높아지고 있고 있다. 이에 본 연구에서는 가스터빈 제어에 사용되고 있는 듀얼 온도센서가 고장이 났을 경우 센서의 고장을 정확하게 진단하고 체계적으로 검출할 수 있는 퍼지로직 기반의 고장진단 알고리즘을 제안하였으며, 제안된 알고리즘의 유용성 확인을 위해 Matlab/Simulink의 환경에서 다양한 시뮬레이션을 수행함으로 제안된 알고리즘의 유용성을 확인하고자 하였다.

• 한국컴퓨터정보학회논문지
• /
• 제4권1호
• /
• pp.47-53
• /
• 1999

의학분야에서 컴퓨터는 병원에서 발생하는 각종 업무데이터의 전산화에서 진단을 위해 사용하는 검사 의료기기들의 자동화, 그리고, 각종 의학영상들을 디지털화하여 처리하는 단계까지 활발하게 활용되고 있는 실정이다. 이러한 시점에서 본 논문에서는 병원의 임상병리과에서 늘어나고 있는 혈액검사를 자동화하기 위한 것으로 혈구영상으로부터 적혈구를 분석하여 정상세포를 비롯한 비정상세포를 16부류로 나누어 분류하였다. 이를위해 UNL푸리에 특징과 불변 모멘트 알고리즘을 사용하여 세그먼트된 적혈구 영상으로부터 특징을 추출하고 이를 인식하기 위한 다단계 신경망을 구축하였다. 실제 임상에서 10명의 환자를 대상으로 실험한 결과 검사자가 참조가능 형태의 결과를 얻을 수 있었다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1221-1224
• /
• 2004

This paper presents the programmable logic controller (PLC) networking development for communication with the mobile phone. The proposed technique is suitable for remote sensing control systems, which can display the operation status and monitoring fault diagnosis of a system. The system operation is based on the use of personal computer (PC) to logically analyze data from PLC, and existing internet protocol for sending information messages to mobile phones.

• 대한의용생체공학회:의공학회지
• /
• 제17권2호
• /
• pp.179-188
• /
• 1996

A clinically oriented 32-channel electroencephalogram (EEG) and evoked potential (EP) mapping system has been developed EEG and EP signals acquired from 32-channel electrodes attached on the heroid surface are amplified by a pre-amplifier which is separated from main amplifier and is located near the patient to reduce signal attenuation and noise contamination between electrodes and the amplifier. The amplified signals are further amplified by a main amplifier where various filtering and gain contr61 are achieved An automatic artifact rejection scheme is employed using neural network-based EEG and artifact classifier, by which examination time is substantially reduce4 The continuously measured EEG sigrlals are used for spectral mapping, and auditory and visual evoked potentials measured in synchronous to the auditory and visual stimuli are used for temporal evoked potential mapping. A user-friendly graphical interface based on the Microsoft Window 3.1 is developed for the operation of the system. Statistical databases for comparisons of group and individual are included to support a statistically-based diagnosis.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1992년도 추계학술대회
• /
• pp.89-92
• /
• 1992

The sensory nerve study is the important index to diagnosis peripheral neuromyotic disease. This paper discusses about the design of parameter - latency, amplitude, conduction velocity - measurement system in the sensory nerve. This system consists of three parts which are Main Control Unit(MCU), Stimulator, and external output unit. Also new measurement algorithms which is adaptive threshold method is presented in this paper. The designed system is controlled by MCU includes automatic detection algorithms and self-diagnostic functions.