• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.210-212
• /
• 2007

본 논문에서는 컴퓨터 바이러스 정보 구축과 탐색에 학습기능을 도입함으로 새로 발생하는 바이러스를 찾아내어 대처할 수 있도록 설계된 퍼지 진단 시스템 FDS를 제안한다. FDS에서는 FCM 알고리즘을 사용하여 알려진 정보의 클러스터를 형성하고 이에 전문가의 지식을 포함하는 지식베이스를 구축한다. 진단을 위한 컴퓨터 파일에 대하여 그 파일의 결정 상태를 확인하고 이미 저장된 지식베이스를 바탕으로 바이러스 침입에 대한 정보를 보고하도록 설계되어있다. 이 시스템은 이미 알려진 테스트 데이터와 이전에 알려지지 않은 새로운 테스트 데이터를 실험데이터로 준비하여 그 성능을 테스트 한다. 제안된 시스템이 알려지지 않은 컴퓨터 바이러스의 경우도 효과적으로 진단할 수 있는 타당성을 보이고 있다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.05a
• /
• pp.68-71
• /
• 2002

의사들은 환자들의 건강 상태와 관련하여 다양한 유형의 정보들을 수집하고 분석하여 개별적인 환자들의 진단을 내리게 된다. 의사들이 한 명의 환자와 관련된 다양한 정보로부터 질환을 결정 내리기까지에는 여러 단계에서 다양한 의사결정이 필요하며 매우 복잡한 과정을 거치게 된다. 그러므로 의사들에게 또는 환자들에게 보조적인 도움을 주고자 많은 의료진단 시스템들이 개발되었다. 현재까지 개발된 대부분의 의료 진단시스템들은 특정한 의사의 경험이나 한 유형의 질환에 고정되어 있다. 그래서 환자들이 급성복통과 같은 여러 가지 유형의 질환에 관련되어 있는 증상을 호소할 때 의사들이 적절한 의사결정을 내리기가 쉽지 않다. 본 논문에서는 급성복통과 관련된 여러 가지 유형의 질환을 진단할 수 있는 시스템을 퍼지 논리를 이용하여 설계하고 구현해 본다.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.2
• /
• pp.615-621
• /
• 2014

Power transformer is one of the most important equipments in electrical power system. The detection of certain gases generated in transformer is the first indication of a malfunction that may lead to failure if not detected. Dissolved gas analysis (DGA) of transformer oil has been one of the most reliable techniques to detect the incipient faults. Many conventional DGA methods have been developed to interpret DGA results obtained from gas chromatography. Although these methods are widely used in the world, they sometimes fail to diagnose, especially when DGA results falls outside conventional method codes or when more than one fault exist in transformer. To overcome these limitations, fuzzy inference system (FIS) is proposed. 250 different cases are used to test the accuracy of various DGA methods in interpreting the transformer condition.

• Journal of Korean Institute of Industrial Engineers
• /
• v.27 no.1
• /
• pp.61-68
• /
• 2001

A rotor system is composed of a rotating shaft with supporting bearings. The rotor system is widely used in every rotating machinery such as the turbine generator and the high precision machine tools. A negligible error or malfunction in the rotor, however, can cause a catastrophic failure in the system then result in the environmental and economic disasters. A diagnosis of the rotor system is important in preventing these kinds of failures and disasters. Up to now, many researchers have devoted in the development of diagnosing tools for the system. The basic principles behind the tools are to retrieve the data through the sensors for a specific state of the system and then to identify the specific state through the heuristic methods such as neural network, fuzzy logic, and decision matrix. The proper usage of the heuristic methods will enhance the performance of the diagnostic procedure when together used with the statistical signal processing. In this paper, the methodologies in using the above 3 heuristic methods for the diagnostics of the rotor system are established and also tested and validated for the data retrieved from the rolling element bearing and journal bearing supported system.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.12 no.2
• /
• pp.38-44
• /
• 1998

This paper presents an integrated fault diagnosis expert system to assist SCADA operators in local control centers which controls unmanned distribution substations in a power system. The proposed system diagnoses various faults occurred in both substation devices and transmission devices. The system can be easily installed without disturbing main SCADA system. The system simply shares the dynamic information including alarms with main SCADA using dual data link interface. And the proposed expert system utilizes the fuzzy reasoning process in order to consider the uncertainty factor. The system is developed using a low cost personal computer owing to the special modular programming and the meta-inf!'lrence structure. Case studies showed a promising possibility.bility.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.4 no.4
• /
• pp.885-893
• /
• 2000

The use of neural-fuzzy system to model mesh seam welding is described in this paper. Conventional, automated process generally involves sophisticated sensing and control techniques applied to various processing parameters. Welding parameters affecting quality include the arc voltage, the welding current, torch travel speed and the pressure and so on. The relationship between the welding parameters and weld quality is not a direct one, and in addition, the effect of the weld parameter variables are not independent of the each other. The effectiveness of the proposed neuro-fuzzy algorithms is demonstrated by computer simulations.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.995-998
• /
• 1995

As the modern industrial processes become more complex, it is getting more difficult to model and control the processes. Naturally, an advanced type of DCS(Distributed Control System) with higher level functions is being sought Advanced DCS is a DCS with advanced functions such as fault diagnosis, GPC(Generalized Predictive Control), NN(Neural Network), and Fuzzy Control. In this thesis, we have studied a fuzzy control algorithm for realizing an advanced DCS. Its algorithm is implemented in a form of function code which is a process control language, being used by the industrial engineers. To verify the realized function code of the fuzzy control, the function code is applied to a continuous casting process of the Pohang Iron & Steel Works in Kwangyang. The rules of the fuzzy control were collected via interviews of the field operators and their operation documents. Finally, usability of the function code of the fuzzy control is shown via simulation for the continuous casting process model.

• Journal of Intelligence and Information Systems
• /
• v.8 no.1
• /
• pp.65-65
• /
• 2002

본 논문에서는 용해로 이상감시를 위한 실시간 유리 용해로 운전 전문가시스템을 구축한 결과를 소개한다. 유리 용해 공정에서는 운전자의 경험지식에 의해 내부의 상황을 판단하게 되고, 이는 용해로 수명과 제품의 품질에 중요한 영향을 준다. 이를 전문가 시스템으로 구현하기 위하여, 먼저 기존 운전자의 지식을 취합, 분석한다. 그 후,취합된 각 지식들의 특성에 부합하도록 이진 규칙(Crisp Rule)과 퍼지 규칙(Fuzzy Rule)으로 구분한다. 이 때, 선형 회귀분석을 통하여 퍼지 규칙의 입력을 결정함으로써 보다 정확한 운전 지식의 표현이 가능하도록 하였다. 설계된 알고리듬은 젠심(Gensym)사의 실시간 전문가 시스템 개발 툴인 G2를 사용하여 구현하였다. 제시된 퍼지 전문가 시스템은 삼성코닝(주) 수원사업장의 실제 생산 용해 공정에 직접 적용하여 그 효율성이 검증되었다.

• Journal of KSNVE
• /
• v.5 no.3
• /
• pp.361-371
• /
• 1995

The vibration of reactor internals should be monitored and diagnosed for the early detection of the failure of reactor pressure vessel. This can be performed by analyzing the time-history signals from the excore neutron flux detertors. The conventional method is an on-demand system which generates power spectra through Fast Fourier Transform(FFT) algorithm. The operator can make his own decision to detect abnormal vibration using these spectra. This post- processing method, however, requires special expertise in the reactor noise analysis and signal processing for random data. It may mislead the operator into erroneous decision-making, if he is a novice in reactor noise analysis. Hence this study is focused on the automated monitoring and diagnosis procedure for the reactor noise analysis, especially on the Fuzzy algorithm to recognize the pattern of the vibration of Core Suport Barrel. The excore neutron signals of Yonggwang Nuclear Power Plant unit 3 is acquired and analyzed using conventional FFT spectra and tested to adopt the Fuzzy method. An Automated Monitoring and Diagnosis System for CSB Vibration using this Fuzzy method is proposed. Furthermore, vibration data for CSB of Youggwang Nnclear Power Plant unit 3 is presented.

• Journal of the Korean Society of Industry Convergence
• /
• v.4 no.4
• /
• pp.403-411
• /
• 2001

A criterion for evaluation of burners has changed recently, and the environmental problems are raised as a global issue. Burners with higher thermal efficiency and lower oxygen in the exhaust gas, evaluated better. To comply with environmental regulations, burners must satisfy the $NO_x$ and CO regulation. Consequently. 'good burner' means one whose thermal efficiency is high under the constraint of $NO_x$ and CO consistency. To make existing burner satisfy recent criterion, it is highly recommended to develop a feedback control scheme whose output is the consistency of $NO_x$ and CO. This paper describes the development of a real time flame diagnosis technique that evaluate and diagnose the combustion states, such as consistency of components in exhaust gas, stability of flame in the quantitative sense. In this paper, it was proposed on the flame diagnosis technique of burner using Neuro- Fuzzy algorithm. This study focuses on the relation of the color of the flame and the state of combustion. Neuro- Fuzzy learning algorithm is used in obtaining the fuzzy membership function and rules. Using the constructed inference algorithm, the amount of $NO_x$ and CO of the combustion gas was successfully inferred.