• 소음진동
• /
• 제5권4호
• /
• pp.543-553
• /
• 1995

Modern steam turbine generators are being built as a higher power and larger system, experiencing more frequent starts and stops of operation due to a constant change of power demands. Hence, they are inevitably more vulnerable to various vibrations, and more often exposed to the danger of sudden vibration accidents than ever before. Even under the circumstances, in order to secure the system reliability of steampower plants and there by to supply safely the public electricity, it is important to prevent a sudden vibration accident in one hand and even when it happens, to raise an operating efficiency of the plants throught swift and precise treatments in the other. In this study, an interactive vibration diagnostic system has been developed to make the on-site vibration diagnosis of steam turbine generators possible and convenient, utilizing a note-book PC. For this purpose, at first the principal vibration phenomena, such as various unbalance and unstable vibrations as well as rubbing, misalignment, and shaft crack vibrations, have been systematically classified as grouped parameters of vibration frequencies, amplitudes, phases, rotating speeds at the time of accident, and operating conditions or condition changes. A new complex vibration diagnostic table has been constructed from the causal relations between the characteristic parameters and the principal vibration phenomena. Then, the diagnostic system has been developed to screen and issue the corresponding vibration phenomena by assigning to each user-selected combination of characteristic parameters a unique characteristic vector and comparing this vector with a diagnostic vector of each vibration phenomenon based on the constructed diagnostic table. Moreover, the diagnostic system has a logic whose diagnosis may be performed successfully by inputing only some of the corresponding characteristic parameters without having to input all the parameters. The developed diagnostic system has been applied to perform the diagnosis of several real cases of steam turbine vibration accidents. And the results have been quite satisfactory.

• 한국품질경영학회:학술대회논문집
• /
• 한국품질경영학회 2010년도 춘계학술대회
• /
• pp.254-261
• /
• 2010

The increase in hazard level is attributed to the industrial hazard environment; complete national environmental hazards to human health include climate change. The damage level in Korea from 1993 to 2009 has exceeded the Increase In adverse environmental conditions. Priority areas of concern will include those risks that are most likely to occur and are expensive when they do take place such as accident or injury at a community pool. Therefore, in this paper, we suggest the System Engineering method for application to the railway RAMS. Recently, the requirement of high-integrity level of infrastructure has been deemed important. The systems level approach is defined through the assessment of the RAMS interactions between elements of complex system applications.

• Current Photovoltaic Research
• /
• 제7권2호
• /
• pp.38-45
• /
• 2019

In this paper, we analyzed the present status of the safety manager and safety assurance aspects through a complex analysis on the operational aspects, marketability and electrical safety aspects of photovoltaic power generation facilities. In the analysis of the equipment status, we analyzed the status and operated status of the installed PV system in Korea and the correlation between the safety manager and the accident. In addition, we analyzed the direction of the ESS through the analysis of the installation status of the ESS, and applied it to the interpretation part of the ESS associated with the solar power generation. The status of the electric safety manager can be used to analyze the data for selecting the electric safety manager by capacity by analyzing the accident status, the electric safety manager operation status, the safety management time by capacity, and the electric safety manager market.

• 지능정보연구
• /
• 제21권4호
• /
• pp.1-16
• /
• 2015

교통사고의 원인을 규명하고 미래의 사고를 방지하기 위한 노력의 일환으로 데이터 마이닝 기법을 이용한 교통 데이터 분석의 연구가 이루어지고 있다. 하지만 기존의 교통 데이터를 이용한 마이닝 연구들은 학습된 결과를 사람이 이해하기 어려워 분석에 많은 노력이 필요하다는 문제가 있었다. 본 논문에서는 많은 속성들로 표현된 교통사고 데이터로부터 유용한 패턴을 발견하기 위해 규칙 학습 기반의 데이터 마이닝 기법인 연관규칙 학습기법과 서브그룹 발견기법을 적용하였다. 연관규칙 학습기법은 비지도 학습 기법의 하나로 데이터 내에서 동시에 많이 등장하는 아이템(item)들을 찾아 규칙의 형태로 가공해 주며, 서브그룹 발견기법은 사용자가 지정한 대상 속성이 결론부에 나타나는 규칙을 학습하는 지도학습 기반 기법으로 일반성과 흥미도가 높은 규칙을 학습한다. 규칙 학습 시 사용자의 의도를 반영하기 위해서는 하나 이상의 관심 속성들을 조합한 합성 속성을 만들어 규칙을 학습할 수 있다. 규칙이 도출되고 나면 후처리 과정을 통해 중복된 규칙을 제거하고 유사한 규칙을 일반화하여 규칙들을 더 단순하고 이해하기 쉬운 형태로 가공한다. 교통사고 데이터를 대상으로 두 기법을 적용한 결과 대상 속성을 지정하지 않고 연관규칙 학습기법을 적용하는 경우 사용자가 쉽게 알기 어려운 속성 사이의 숨겨진 관계를 발견할 수 있었으며, 대상 속성을 지정하여 연관규칙 학습기법과 서브그룹 발견기법을 적용하는 경우 파라미터 조정에 많은 노력을 기울여야 하는 연관규칙 학습기법에 비해 서브그룹 발견기법이 흥미로운 규칙들을 더 쉽게 찾을 수 있음을 확인하였다.

• International Journal of Reliability and Applications
• /
• 제3권1호
• /
• pp.25-35
• /
• 2002

This paper presents a dynamic reliability assessment methodology for use in the safety assessment of a complex system such as a nuclear power plant. The method is applied to a dynamic analysis of the potential accident sequences that may occur during mid-loop operation in a nuclear power plant. The idea behind this approach consists of both the use of the concept of the performance achievement/requirement correlation and of a dynamic event tree generation method. The assessment of the system reliability depends on the determination of both the required performance distribution and the achieved performance distribution. The quantified correlation between requirement and achievement represents a comparison between two competing variables. It is demonstrated that this method is easily applicable and flexible in that it can be applied to any kind of dynamic reliability problem.

• 한국안전학회지
• /
• 제11권2호
• /
• pp.52-59
• /
• 1996

This paper presents a new approach for assessing the dynamic reliability in a complex system such as a nuclear power plant. The method is applied to a dynamic analysis of the potential accident sequences which may occur during mid-loop operation. Mid-loop operation is defined as an operation to make RCS water level below the top of the flow area of the hot legs at the junction with the reactor vessel for repairs and maintenance of steam generators and reactor coolant pumps for a specific time. The Idea behind this approach consists of both the use of the concept of the performance achievement/requirement correlation and of a dynamic event tree generation method. The assessment of the system reliability depends on the determination of both the required performance distribution and the achieved performance distribution. The quantified correlation between requirement and achievement represents a comparison between two competing variables. It is demonstrated that this method is easily applicable and flexible in that it can be applied to any kind of dynamic reliability problem.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2023년도 봄 학술논문 발표대회
• /
• pp.405-406
• /
• 2023

In the era of AI, intelligent construction safety technologies are being introduced to the construction safety environment, but the application of AI has limitations due to the lack of accident images to learn in complex construction sites. In order to overcome this, we will introduce an intelligent risk detection system that dramatically improves risk detection accuracy by combining AI with digital twin technology, and introduce various cases.

• 한국정보통신학회논문지
• /
• 제11권11호
• /
• pp.2078-2082
• /
• 2007

현재 교통사고의 통계를 보면 야간에 발생하는 교통사고는 주간과 비슷하게 일어나지만, 치사율은 주간에 비해 1.5배 높은 실정이다. 이러한 문제점은 야간에 운전자의 시야확보가 불리하여 적절한 사고 대응을 하지 못하는데 기인한다. 그러므로 본 논문에서는 밝기, 연색성, 광효율이 우수한 자동차 전조등을 마이크로컨트롤러에 의한 디지털 제어방식을 적용하여 주어진 요구조건 및 주변 환경에 최적으로 적용할 수 있도록 전자식 지능형 적응제어시스템을 설계하였다. 특히, 자동차용 조명장치의 경우 기본적인 역할은 물론 주행조건, 도로조건 및 기후조건에 가장 적합한 조명 패턴으로 자동적으로 전환 및 이동시켜 줄 수 있는 지능적인 조명장치를 구현하여야 한다. 따라서 본 논문에서는 이러한 지능형 자동차의 구현에 초점을 맞추어 운전자의 편의성과 안전성을 더욱 향상시킨 조명장치 시스템의 개발에 목표를 두었다.

• 컴퓨터교육학회논문지
• /
• 제17권6호
• /
• pp.115-122
• /
• 2014

현 청소년들의 학교내 생활환경에서 문제점으로 대두되는 폭력 및 자살사고 발생률 증가에 대한 예방차원의 빅 데이터 처리 분석 시스템을 목표로 연구하였고 설계의 경제성과 용이성, 적용의 신속성 등을 고려해서 많은 이용률을 가지고 있는 오픈 소스인, 하둡 시스템(Hadoop system)의 맵리듀스(MapReduce) 알고리즘과 분산 병렬 환경을 위한 HDFS(Hadoop Distibuted File System) 구성을 사용하여 실험하였다. 연구에서 사용된 분석기법은 기존의 통계적인 분석기법들이 가지는 난이도를 피하기 위해 상업적인 사회 망의 비정형 대화 자료를 이용해서 폭력성 어휘에 대한 단어 수(word count) 분석을 적용하여 폭행, 자살사고를 사전에 감지하여 예방하는 감성분석(sentiment analysis) 시스템을 텍스트 마이닝 관점에서 제안하여 실험하였다.

• 산업경영시스템학회지
• /
• 제40권4호
• /
• pp.147-153
• /
• 2017

The mortality rate in industrial accidents in South Korea was 11 per 100,000 workers in 2015. It's five times higher than the OECD average. Economic losses due to industrial accidents continue to grow, reaching 19 trillion won much more than natural disaster losses equivalent to 1.1 trillion won. It requires fundamental changes according to industrial safety management. In this study, We classified the risk of accidents in industrial complex of Ulju-gun using spatial analytics and data mining. We collected 119 data on accident data, factory characteristics data, company information such as sales amount, capital stock, building information, weather information, official land price, etc. Through the pre-processing and data convergence process, the analysis dataset was constructed. Then we conducted geographically weighted regression with spatial factors affecting fire incidents and calculated the risk of fire accidents with analytical model for combining Boosting and CART (Classification and Regression Tree). We drew the main factors that affect the fire accident. The drawn main factors are deterioration of buildings, capital stock, employee number, officially assessed land price and height of building. Finally the predicted accident rates were divided into four class (risk category-alert, hazard, caution, and attention) with Jenks Natural Breaks Classification. It is divided by seeking to minimize each class's average deviation from the class mean, while maximizing each class's deviation from the means of the other groups. As the analysis results were also visualized on maps, the danger zone can be intuitively checked. It is judged to be available in different policy decisions for different types, such as those used by different types of risk ratings.