• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.1782-1787
• /
• 1997

A combined algorithm called APEXS(Alarm Processing and Diagnosis Expert System) for power plants has been developed on the time-based alarm processing with a proper alarm prioritization and a diagnosis with a qualitative model(QM), qualitative interpreter(QI), and a state-transition trees(STT).

• 한국원자력학회:학술대회논문집
• /
• 한국원자력학회 1997년도 춘계학술발표회논문집(1)
• /
• pp.133-138
• /
• 1997

For a long time, a number of alarm processing techniques have been researched to reduce the number of actuated alarms for operators to deal with effectively during the abnormal as well as the normal conditions. However, the strategy that the only systems with a few clear technologies should be used as a part of an alarm annunciation system has been adopted considering the effectiveness and the reliability in actual alarm processing systems. Therefore, alarm processing systems have difficult knowledge-base maintenance problems and limited expansion or enhancement defects. To solve these shortcomings, the integrated knowledge-base which can express the general information related to all the alarm processing techniques is proposed and its management tool, Knowledge Input Tool for Alarm (KIT-A) which can handle the data of the knowledge-base efficiently is developed. Since the integrated knowledge-base with KIT-A can manipulate all the alarm information without the modification of alarm processing system itself, it is expected to considerably advance the overall capability of maintenance and enhancement of the alarm processing systems.

• 전자공학회논문지B
• /
• 제32B권8호
• /
• pp.1045-1056
• /
• 1995

The purpose of multiple alarm processing is to give the operator the correct information and perception of the malfunction present in the plant. In this thesis, an APS(Alarm Processing System) is studied for fossil power plants. This APS is based on a cause-consequence trees in the knowledge representation aspect for alarm and plant and adapts alarm filtering methods using fired time information in the decision aspect. Through the cause-consequence trees and filtering methods, the Alarm Processing System finds the cause alarm among the fired multiple alarms and calculates the cause degree which represents the possibility of a fault occurring in the instruments of the plant with the information of fired alarm. The knowledge base is built via interviews and questionaries with the expert operators on the Seoul power plant unit 4. Finally, the validity of the studied APS is shown via simulations.

• 전기학회논문지
• /
• 제60권10호
• /
• pp.1804-1810
• /
• 2011

It is necessary to adopt some logical techniques and methods of alarm processing for a large complex plant such as nuclear power plants in order to present the occurred alarm messages properly and concisely. Among such alarm processing techniques, the alarm suppressing function is a strong tool to avoid alarm flooding during the sudden transients of plant output power such as turbine trips, reactor trips and other incidents. Unless any suppression or representation technologies are used in an alarm message listing system, it cannot provide quick assistance to plant operators or supervisors during plant upsets because too many alarm messages are presented in an alarm list window. This paper presents the key suppression methods and analysis processes developed for implementing a suppressed alarm message listing function of an integrated alarm system called LogACTs which has been applied to a CANDU nuclear power plant. A simulation testing of the suppressing function conducted with the real plant alarm message list data has demonstrated an effective performance of the developed logics with the high suppression rate.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 제37회 하계학술대회 논문집 A
• /
• pp.161-162
• /
• 2006

There are many alarms in Substation Automation System because of data types and quantities increasing, so it is very difficult for operators to know the actual situations. In order to help operators easily make decision, some unnecessary alarms should be removed or combined as one. In this paper, alarm processing is using the structure of substation system and the relation of measured data and events to make some rules. Conventional alarm processing just gives data, but proposed alarm processing gives the whole information. In a simulation model system, the data such as voltage, current and CB status are collected by HyperSim and saved in DB, then proposed alarm processing has been testified using those data based on real-time simulation.

• 한국콘텐츠학회논문지
• /
• 제2권1호
• /
• pp.86-97
• /
• 2002

본 논문에서는 먼저 국제 표준화기구인 ITU-T G.805의 계층화와 분할화 개념을 근간으로 초고속정보통신망 관리모델을 제시한다. 그리고 초고속정보통신망에서의 VP와 VC에 대한 구성 정보모델과 장애를 관리하기 위한 정보모델을 기술한다. 효율적인 장애를 관리하기 위해서 여기서는 두 가지종류로 알람을 구분하였다. 하나는 제공 중인 서비스에 직접적인 영향을 줄 수 있는 장애성 알람과 서비스에는 직접적으로는 영향을 주지 않는 경보성 알람으로 나누었다. 그리고 이들 알람을 처리하기 위해 장애성 알람처리 시스템과 경보성 알람처리 시스템에 대한 두 가지 연산모델을 제안한다. 또한 장애가 발생하였을 경우, 알람을 처리하는 절차에 대해서 기술하고 장애가 발생한 VP와 VC연결에 대한 연결 재설정 시 NMS와 SubNMS의 처리 범위와 처리과정에 대해서 기술한다. 끝으로 제안된 장애성 알람처리 시스템을 구현하고 알람 발생율에 따라 우선순위별 알람처리 시간을 비교한다.

• Nuclear Engineering and Technology
• /
• 제55권10호
• /
• pp.3716-3724
• /
• 2023

Loose parts monitoring and detecting alarm type in real Nuclear Power Plant have challenges such as background noise, insufficient alarm data, and difficulty of distinction between alarm data that occur during start and stop. Although many signal processing methods and alarm determination algorithms have been developed, it is not easy to determine valid alarm and extract the meaning data from alarm signal including background noise. To address these issues, this paper proposes a denoising autoencoder-based majority vote classification. Training and test data are prepared by acquiring alarm data from real NPP and simulation facility for data augmentation, and noisy data is reproduced by adding Gaussian noise. Using DAEs with 3, 5, 7, and 9 layers, features are extracted for each model and classified into neural networks. Finally, the results obtained from each DAE are classified by majority voting. Also, through comparison with other methods, the accuracy and the false alarm rate are compared, and the excellence of the proposed method is confirmed.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제12권4호
• /
• pp.229-240
• /
• 2006

개량형 경보시스템은 원자력 플랜트의 경보 기능을 구현하기 위하여 최신 디지털 기술들을 적용한다. 신호검증 및 선진 경보처리 기술들을 제공하는 디지털 신기술의 사용은 제어실 운전원 연계를 향상시킨다. 본 논문은 원자력 플랜트의 개량형 경보시스템의 설계 공정, 신뢰도 예측 도구를 이용한 시스템 신뢰도 및 가용도 향상 평가, 인간공학적 성능 관점의 설계 전략 그리고 검증설비를 이용한 성능 분석의 결과 등과 같은 실제적인 구현 사례를 소개한다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2014년도 추계학술발표대회
• /
• pp.1096-1099
• /
• 2014

스마트폰의 보급률에 맞물려 스마트폰 사용으로 인한 보행자 교통사고가 증가함에 따라 전세계적으로 이에 관한 연구 또한 꾸준히 증가 추세임에도 불구하고 인구대비 스마트폰 보급률이 세계 최고인 국내에서는 이에 대한 연구가 아직 미흡한 실정이다. 본 연구에서는 보행 중 교통사고 중에서 큰 비중을 차지하고 있는 젊은층의 산만 보행에 관해 알아보고자 하였다. 본 연구는 정신과학 분야의 주의 네트워크 연구를 바탕으로 보행자의 안전도 향상은 물론, 스마트폰 이용자의 사용성을 고려한 depth-based alarming 서비스를 제안한다.-본 연구는 스마트폰 애플리케이션을 제작하여 국내 20대 스마트폰 이용자를 대상으로 피험자내 설계로 진행되었고, 보행자의 안전도에 관련한 무선조종 자동차에 대한 반응속도와 충돌여부를 측정하였고, 또한 앱 사용성에 관련한 방해도 및 만족도를 설문을 통해 측정하였다. 본 연구는 위험 상황을 알리는 alarm 을 제공하기 전에 미리 pre-alarm 을 제공하는 depth-based alarming 을 디자인 하였다. 본 연구는 실험을 통해 pre-alarm 제공시 alarm 에 대한 보행자의 반응 속도가 1.446 초 향상됨을 통계적 유의성을 통해 입증함으로써 pre-alarm 을 제공하는 depth-based alarming 서비스의 필요성을 제시한다.

• Nuclear Engineering and Technology
• /
• 제51권1호
• /
• pp.146-154
• /
• 2019

An improved principal component analysis (PCA) method is applied for sensor fault detection and isolation (FDI) in a nuclear power plant (NPP) in this paper. Data pre-processing and false alarm reducing methods are combined with general PCA method to improve the model performance in practice. In data pre-processing, singular points and random fluctuations in the original data are eliminated with various techniques respectively. In fault detecting, a statistics-based method is proposed to reduce the false alarms of $T^2$ and Q statistics. Finally, the effects of the proposed data pre-processing and false alarm reducing techniques are evaluated with sensor measurements from a real NPP. They are proved to be greatly beneficial to the improvement on the reliability and stability of PCA model. Meanwhile various sensor faults are imposed to normal measurements to test the FDI ability of the PCA model. Simulation results show that the proposed PCA model presents favorable performance on the FDI of sensors no matter with major or small failures.