• 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.

• The Journal of Korean Association of Computer Education
• /
• v.22 no.1
• /
• pp.63-78
• /
• 2019

This study aims to improve User eXperience (UX) of the diagnostic-supplement learning system for Basic academic skills which has been utilized by teachers nationwide since 2015 in order to provide a consistent and systematic support on students' basic academic skills in K-12 school contexts. To achieve the research objective, usability evaluations such as basic questionnaire about UX/UI of the system according to user types, user testing, in-depth interview, expert heuristics were conducted. In addition, user-centered system was suggested through developing and iteratively evaluating the prototypes based on the user requirements drawn from the findings of such quantitative and qualitative usability evaluations. This study has an implication in suggesting the user-friendly design through the UX/UI improvements of the diagnostic-supplement learning system for Basic academic skills.

• Journal of Sasang Constitutional Medicine
• /
• v.28 no.1
• /
• pp.1-10
• /
• 2016

Objectives SCAT (Sasang Constitution Analysis Tool) is a system designed to provide the information needed to diagnose a sasang constitution diagnosis expert diagnosis. In order to determine the sasang constitution diagnosis requires the following four ways. This system provides objective information to the constitution diagnostic expert to collect such information.Methods SCAT was constructed by considering the user UI/UX to be easy to enter information. To provide a state of the subject in Table to make it easier to grasp the information of the subject also in constitution diagnostician.Results Provides objective data for experts to determine the constitutional history of the subject.Conclusions Professionals and ordinary users through the SCAT system can easily access the sasang constitution diagnosis. In the future through the advancement of the SCAT system will improve the user's convenience stability.

• Journal of Korea Society of Industrial Information Systems
• /
• v.6 no.3
• /
• pp.35-43
• /
• 2001

This thesis proposes a diagnostic formula for student's responses based on linguistic variable concept of fuzzy that makes domain expert to input the kernel elementeasily that constructs domain independent student module. And the domain expert can construct the rule with linguistic variable that is used to inference student's recognition state. This study designs a student module that can inference student's recognition state using this rule represented by linguistic variable.

• Proceedings of the KIEE Conference
• /
• 2001.07c
• /
• pp.1676-1678
• /
• 2001

In general, power demand is on an increasing trend as industries have made rapid strides. Power transformer is the most important equipment in substation for this reason. Transformer trobles go with blackout, expensive repair costs and huge economic losses. Therefore it is important to find the quick detection of incipient fault for the least losses. There have been gas, partial discharge, temperature, OLTC, fan and pump diagnosis for preventive techniques by present. Specially gas analysis has been adapted for a long time and proved as confident method. In this paper, we analysed the fault causes of used power transformer. The insulation faults was occupied 40% of inquired 152 faults from 1991 to 2000. This study presents the developed algorithm and expert system for finding abnormal status within transformer. We used the Element Expert tool developed Neuron DATA Inc.

• Proceedings of the KIEE Conference
• /
• 2000.07c
• /
• pp.1903-1905
• /
• 2000

Power transformers have a tendency of ultra-high voltage capacity as power demand increases day after day KEPCO also will have plan to supply transmission power from 345KV to 765KV in the early of 2000. Therefore, the fault by insulation destruction gives rise to large area of power failure in huge capacity transformers. On-line predictive diagnostics is very important in power transformers because of economic loss and its spreading effect. This study presents the algorithm for transformer oil analysis used KEPCO code, IEC code, gas pattern method and Dornenburg & Roger Ratio method. We also describe the MMI display of expert system programmed by Element Expert Tool(Neuron Data Inc.).

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.32.5-32
• /
• 2002

Processing plasmas are playing a crucial role in either depositing thin films or etching fine patterns. Any variability in process factors (such as radio frequency power or pressure) can cause a significant shift in plasma state. When this shift becomes large enough to change operating condition beyond an acceptable level, overall product quality can greatly be jeopardized. Thus, timely and accurate diagnosis of plasma malfunction is crucial to maintaining device yield and throughput. Many diagnostic systems have been developed, including HIPOCRATES [1] and PIES [2]. Plasma equipment was also diagnosed by combining neural network and expert system called Dempster-Schafer Theory [3]. A fact c...

• The Proceedings of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.11 no.2
• /
• pp.80-88
• /
• 1997

본 연구에서는 유중 가스 분석법으로 전력용 변압기의 고장 진단을 위한 전문가 시스템을 개발하였다. 유중 가스 분석법을 적용할 때 나타나는 가스 구성비 및 주요 가스 판정 기준, 고장 진단 규칙의 불확실성은 퍼지 집합 및 퍼지 척도를 이용하여 처리하였다. 또한 변압기의 고장 진단 결과는 사고 및 정상을 나타내는 정량화된 지수로 표현하였다. 제안된 고장 진단 전문가 시스템은 한국 전력 공사의 변압기 유중 가스 기록으로 효용성을 입증하였다.

• Korean Journal of Agricultural Science
• /
• v.45 no.4
• /
• pp.879-888
• /
• 2018

This research was done to develop a standard management checklist for duck farmers. To this end, experts in commercial duck farming participated in making a blueprint for a standard management checklist. This expert group consisted of ten members which included the researcher, a professor, an extension advisor and leading farmers in commercial duck farming. By collecting knowledge on commercial duck farming from these experts, a management performance index was made, and checking factors were designated. As a result of this expert survey, management outcome indicators and subdivision evaluation indicators were established. To confirm these results, a first stage Delphi expert survey was carried out. As a result, the experts were not in agreement with the farming scale of 1 - 4 levels and 2 levels in the management outcome indicators. Additionally, the experts were not in agreement on the choice of feed in the feeding management and the cooperative management system as well as the utilization of agricultural information in managing the business. The factors that did not have the same opinion among experts were surveyed by a second Delphi survey asking whether experts approve the requested value. As a result of the second Delphi survey, all factors have an approval rate that have a value of more than 90%. Finally, a standard management checklist was established based on the research result.

• Journal of Intelligence and Information Systems
• /
• v.5 no.2
• /
• pp.29-42
• /
• 1999

현재 산업의 고도상장과 함께 주기적으로 고장을 진단하여야 하는 기기의 수와 종류도 급속도로 증가하고 있다. 이에 따라 여러 산업 분야에서 고장진단 시스템의 이용이 늘고 있는 추세이다. 이러한 고장진단 시스템은 경험적 고장진단 방식과 모델기반 고장 진단 방식으로 크게 나눌 수 있다. 경험적 고장진단 방식은 전문가가 경험한 사실의 범주에서는 신속하게 고장의 원인을 진단할 수 있지만 전문가가 경험하지 못했던 상황에 대해서는 융통성 있게 진단하지 못한다. 한편 기기의 물리적 기능적 지식을 기반으로 하는 모델기반 고장진단 방식을 변화하는 상황에 적절하게 대처하여 고장의 원인을 진단할 수 있다. 그러나 모델기반 고장진단 방식을 기기의 구조로부터 증상들을 추론하여 원인을 파악하므로 탐색 범위가 넓어 진단속도가 늦다는 단점이 있다. 본 연구에서는 이러한 경험적 고장진단 방식과 기기의 모델기반 고장진단 방식의 장점을 결합하여 신속하고 정확하게 고장진단을 할 수 있는 통합방식 고장진단 시스템을 제시한다. 통합방식 고장진단 시스템은 대상 기기의 진단 상태에 따라서 동적으로 적절한 진단 방식을 선택하기 위해서 블랙보드 추론기관을 이용한다. 또한 각 진단방식이 생성하는 가설 및 사실들을 효과적으로 통합하여 추론하기 위해서 제어지식을 정의하여 적용한다. 그리고 사용자와 진단 시스템간에 원활한 의사소통을 위해서 멀티미디어 기반 인터페이스를 채용하여 통합방식 진단 시스템을 구축한다.