http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : 구서룡 (검색결과 15 건)
- 무료
- 기관 내 무료
- 유료
-
-
원전 안전-필수 소프트웨어의 품질향상을 위한 최적화된 확인 및 검증 방안
구서룡,유영제,Koo, Seo-Ryong,Yoo, Yeong-Jae 한국시뮬레이션학회 2015 한국시뮬레이션학회 논문지 Vol.24 No.4
As the use of software is more wider in the safety-critical nuclear fields, so study to improve safety and quality of the software has been actively carried out for more than the past decade. In the nuclear power plant, nuclear man-machine interface systems (MMIS) performs the function of the brain and neural networks of human and consists of fully digitalized equipments. Therefore, errors in the software for nuclear MMIS may occur an abnormal operation of nuclear power plant, can result in economic loss due to the consequential trip of the nuclear power plant. Verification and validation (V&V) is a software-engineering discipline that helps to build quality into software, and the nuclear industry has been defined by laws and regulations to implement and adhere to a through verification and validation activities along the software lifecycle. V&V is a collection of analysis and testing activities across the full lifecycle and complements the efforts of other quality-engineering functions. This study propose a methodology based on V&V activities and related tool-chain to improve quality for software in the nuclear power plant. The optimized methodology consists of a document evaluation, requirement traceability, source code review, and software testing. The proposed methodology has been applied and approved to the real MMIS project for Shin-Hanul units 1&2.
-
-
원자력발전소 기동 및 정지 운전을 위한 순환 신경망 기반 인공지능 프레임워크 개발
구서룡,김현민,최건필,김정택 제어·로봇·시스템학회 2019 제어·로봇·시스템학회 논문지 Vol.25 No.9
In order to reduce operator workload from startup and shutdown operations for existing Nuclear Power Plants (NPPs), it is necessary to develop an automation system based on deep learning, the leading approach in current Artificial Intelligence (AI) technology. From existing research, it is challenging to develop an automation system using conventional machine learning for startup and shutdown operation since the automation system needs to be able to handle many instances of both monitoring and control variables in NPPs. Deep learning is able to simulate a variety of operating actions based on the experience of each operator. In this study, an AI framework for an automation system for startup operation in NPPs has been developed using a Recurrent Neural Network (RNN), which is a robust deep learning method for time series analysis. A feasibility study for an AI framework for the automation system is conducted using a Compact Nuclear Simulator (CNS) based on Westinghouse three-loop NPPs. The target scenario for the feasibility study is operation under bubble creation conditions in a pressurizer under startup.
-
-
-
고객정보와 상품네트워크 유사도를 이용한 시장세분화 기법
정석봉,신용호,구서룡,윤협상,Jeong, Seok-Bong,Shin, Yong Ho,Koo, Seo Ryong,Yoon, Hyoup-Sang 한국시뮬레이션학회 2015 한국시뮬레이션학회 논문지 Vol.24 No.4
In recent, hybrid market segmentation techniques have been widely adopted, which conduct segmentation using both general variables and transaction based variables. However, the limitation of the techniques is to generate incorrect results for market segmentation even though its methodology and concept are easy to apply. In this paper, we propose a novel scheme to overcome this limitation of the hybrid techniques and to take an advantage of product information obtained by customer's transaction data. In this scheme, we first divide a whole market into several unit segments based on the general variables and then agglomerate the unit segments with higher QAP correlations. Each product network represents for purchasing patterns of its corresponding segment, thus, comparisons of QAP correlation between product networks of each segment can be a good measure to compare similarities between each segment. A case study has been conducted to validate the proposed scheme. The results show that our scheme effectively works for Internet shopping malls.
-
-
지은경,차성덕,손한성,유준범,구서룡,성풍현 한국정보과학회 2002 정보과학회논문지 : 소프트웨어 및 응용 Vol.31 No.3
Fault tree analysis is the most widely used safety analysis technique in industry. However, the analysis is often applied manually, and there is no systematic and automated approach available to validate the analysis result. In this paper, we demonstrate that a real-time model checker UPPAAL is useful in formally specifying the required behavior of safety-critical software and to validate the accuracy of manually constructed fault trees. Functional requirements for emergency shutdown software for a nuclear power plant, named Wolsung SDS2, are used as an example. Fault trees were initially developed by a group of graduate students who possess detailed knowledge of Wolsung SDS2 and are familiar with safety analysis techniques including fault tree analysis. Functional requirements were manually translated in timed automata format accepted by UPPAAL, and the model checking was applied using property specifications to evaluate the correctness of the fault trees. Our application demonstrated that UPPAAL was able to detect subtle flaws or ambiguities present in fault trees. Therefore, we conclude that the proposed approach is useful in augmenting fault tree analysis. 폴트 트리 분석(Fault Tree Analysis)은 산업계에서 가장 널리 사용되는 안전성 분석 기법 중의 하나이다. 하지만, 이 기법은 보통 수작업으로 이루어지며, 분석 결과를 체계적이고 자동적으로 검증할 수 있는 방법이 없다는 약점을 지닌다. 본 논문에서는 실시간 모델 체커인 UPPAAL을 이용하여 안전성이 중요한 소프트웨어의 요구 사항들을 정형 명세하고, 수작업으로 완성된 폴트 트리의 정확성을 검증하는 방법을 제안하고 있다. 제안된 방법을 유용성을 확인하기 위해서 월성 원자력 발전소의 비상 정지 소프트웨어(Wolsung SDS2)에서 사용된 기능 요구 사항들을 예제로서 사용하였다. 폴트 트리는 월성 SDS2에 대한 전문적인 지식을 지니고 폴트 트리를 이용한 안전성 분석을 여러 번 수행해 본 경험이 있는 대학원생들에 의해 작성되었다. 기능 요구 사항들은 UPPAAL의 입력으로서 사용되기 위해서 시제 오토마타의 형태로 수작업으로 변환되었으며, 이 폴트 트리의 정확성을 검증하기 위해서 모델 체킹을 사용하였다. 본 논문에서 제안된 방법을 월성 SDS2 예제에 적용해 본 결과, 수작업으로 작성된 폴트 트리에 존재하는 오류를 찾을 수 있었으며, 이러한 작업을 통하여 제안된 방법이 폴트 트리 분석에 대한 신뢰도를 높이는데 유용함을 발견하였다.
-
ScienceON연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
