• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2008년도 제39회 하계학술대회
• /
• pp.424-425
• /
• 2008

This paper presents application of RCM(Reliability Centered Maintenance) in waterworks system. The reliability-based probability model for predicting the failure probability is established and FTA(Fault Tree Analysis) is proposed to considering RCM. To calculate failure probability, Weibull distribution is usually used due to age related reliability. FTA is an engineering analysis which is using logic symbols. The real historical data of CMMS(Computerized Maintenance Management System) make full use of case study for waterworks system. Consequently, the RCM would be likely to permit utilities to reduce overall costs in maintenance and improve the total benefit.

• 대한안전경영과학회지
• /
• 제6권3호
• /
• pp.237-247
• /
• 2004

The condition of the manufacturing process in a factory should be diagnosed and maintained efficiently because any unexpected disorder in the process will be reason to decrease the efficiency of the overall system. However, if an expert experienced in this system leaves, there will be a problem for the efficient process diagnosis and maintenance, because disorder diagnosis within the process is normally dependent on the expert's experience. This paper suggests a process diagnosis using data mining based on the collected data from the coil-spring manufacturing process. The rules are generated for the relations between the attributes of the process and the output class of the product using a decision tree after selecting the effective attributes. Using the generated rules from decision tree, the condition of the current process is diagnosed and the possible maintenance actions are identified to correct any abnormal condition. Then, the appropriate maintenance action is recommended using the decision network.

• 산업경영시스템학회지
• /
• 제40권1호
• /
• pp.57-64
• /
• 2017

In order to reduce damages to major railroad components, which have the potential to cause interruptions to railroad services and safety accidents and to generate unnecessary maintenance costs, the development of rolling stock maintenance technology is switching from preventive maintenance based on the inspection period to predictive maintenance technology, led by advanced countries. Furthermore, to enhance trust in accordance with the speedup of system and reduce maintenances cost simultaneously, the demand for fault diagnosis and prognostic health management technology is increasing. The objective of this paper is to propose a highly reliable learning model using various machine learning algorithms that can be applied to critical rolling stock components. This paper presents a model for railway rolling stock component fault diagnosis and conducts a mechanical failure diagnosis of motor components by applying the machine learning technique in order to ensure efficient maintenance support along with a data preprocessing plan for component fault diagnosis. This paper first defines a failure diagnosis model for rolling stock components. Function-based algorithms ANFIS and SMO were used as machine learning techniques for generating the failure diagnosis model. Two tree-based algorithms, RadomForest and CART, were also employed. In order to evaluate the performance of the algorithms to be used for diagnosing failures in motors as a critical railroad component, an experiment was carried out on 2 data sets with different classes (includes 6 classes and 3 class levels). According to the results of the experiment, the random forest algorithm, a tree-based machine learning technique, showed the best performance.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2011년도 정기총회 및 추계학술대회 논문집
• /
• pp.38-46
• /
• 2011

Recently railway operators are doing a lot of researches and studies in order to apply reliability technologies to their maintenance tasks. The maintenance in the aviation and the munitions industry has been developed enough to be benchmarked with the high quality reliability technologies; however, railway industry is still situated in a rudimentary stage with insufficient & limited data. 5678 Seoul Metropolitan Rapid Transit Corporation, which has 17 year experience of the EMU maintenance and system development, has made a constant effort for appling RCM (Reliability Centered Maintenance) to the maintenance for a few years. In this connection, the case study is to be introduced. This paper is based on 'RCM Gateway to World Class Maintenance' by Anthony M. Smith". The reliability technology are applied to the specific EMU and its system by 7 stages; accordingly, applying SMRT's maintenance experience, a unique standard for FMEA(failure mode effect analysis) & LTA(logical tree analysis) is established. Moreover, for reasonable and effective preventive maintenance tasks, the case considering an analysis of failure effects is selected in the final step 7. SMRT will develop reliability technologies through the application of the results to all the EMU systems.

• 정보처리학회논문지D
• /
• 제8D권4호
• /
• pp.377-386
• /
• 2001

공간데이터베이스 시스템에서는 사용자에게 효과적인 공간데이터베이스 접근방법을 제공하기 위하여 공간 뷰를 지원하며 비실체화 방법과 실체화 방법으로 관리한다. 비 실체화 방법은 동일질의에 대한 반복적인 수행으로 서버 병목 현상과 네트워크 부하가 발생하는 문제점이 있고, 실체화 방법은 공간 기본 테이블 변경에 대한 실체화 뷰 관리 방법이 어렵고, 비용이 많이 든다는 문제점이 있다. 본 논문에서는 R-tree 재구성 방법을 이용한 공간 뷰 실체화 관리 기법(SVMT : Spatial View Materialization Technique)을 제안한다. 제안한 SVMT는 공간 뷰 객체 분포율 오차율 이용하여 공간 뷰를 실체화하는 기법으로, 공간 뷰 객체 분포율 오차가 오차 한계 범위내에 존재하면 공간 뷰를 실체화하고 광간 뷰 높이에 해당하는 노드를 공간 뷰에 대한 R-Tree의 루트로 사용하고, 오차 한계 범위를 벗어나면 공간 뷰를 실체화함과 동시에 R-Tree를 재구성하는 방법이다. 이 기법에서 공간 뷰에 대한 정보는 공간 뷰 정보 테이블(SVIT : Spatial View Materialization Technique)를 통하여 관리되며, 이 테이블의 레코드는 공간 뷰에 대한 정보를 저장하고 있다. SVMT는 실체화된 공간 뷰에 대한 질의수행을 통해 공간질의 처리 수행 속도를 빠르게하며, 이를 통하여 반복적인 질의 변환을 통해 발생하는 부가적인 질의 수행 비용을 제거한다. 따라서, 제안하는 기법은 다중 사용자, 동시 작업 환경에서 공간 뷰에 대한 빠른 접근 속도와 빠른 질의 응답을 제공하여 서버의 병목현상과 네트워크 부하를 최소화한다는 장점을 가진다.

• 대한토목학회논문집
• /
• 제43권3호
• /
• pp.397-411
• /
• 2023

국내에서 공용연수 30년 이상인 노후 교량의 수가 급증하고 있다. 이에 따라 교량 노후도, 상태 및 성능 예측을 바탕으로 한 첨단 유지관리 기술의 중요성이 점차 주목받고 있다. 이 연구에서는 머신러닝 기반의 의사결정나무 및 랜덤포레스트 분류 모델을 사용하여 교량의 안전등급을 예측하는 방법을 제안하였다. 일반국도상 교량 8,850개를 대상으로 해당 모델들을 혼동행렬, 균형 정확도, 재현율, ROC 곡선 및 AUC와 같이 여러가지 평가 지표를 통해 분석한 결과 전반적으로 랜덤포레스트가 의사결정나무보다 더 나은 예측 성능을 보유하였다. 특히 랜덤포레스트 중 랜덤 언더 샘플링 기법은 노후도가 비교적 커서 유지관리에 주의를 기울여야 하는 C, D등급 교량에 대해 재현율 83.4%로 다른 샘플링 기법들보다 예측 성능이 더 뛰어난 것으로 나타났다. 제안된 모델은 최근 점검이 실시되지 않은 교량들의 신속한 안전등급 파악 및 효율적이고 경제적인 유지관리 계획 수립에 유용하게 활용될 수 있을 것으로 기대된다.

• 한국지진공학회:학술대회논문집
• /
• 한국지진공학회 2002년도 춘계 학술발표회 논문집
• /
• pp.284-293
• /
• 2002

Using the life cycle cost concept, optimum maintenance and retrofit planning for reliable seismic performance is suggested the overall life cycle cost to be minimized including the initial cost, the costs of inspection, repair, and failure. Limit states of the bridges are defined. And failure probabilities are computed through crossing theory. The effect of maintenance and retrofit is represented using the probability of damage detection and event tree analysis. Optimization of maintenance and retrofit planning method proposed from this research was applied to numerical examples. The analysis incorporates the acceleration and site conditions prescribed in the code, and the quality of inspection methods.

• 대한안전경영과학회:학술대회논문집
• /
• 대한안전경영과학회 2010년도 춘계학술대회
• /
• pp.573-585
• /
• 2010

최근 철도차량은 안전성과 신뢰성 향상을 위해 점차 복잡하게 설계 제작되고, 품질에 대한 기대와 요구수준이 점차 높아짐에 따라 운영기관에서는 과학적이고 체계적인 예방 정비를 통한 안전성과 가용성 향상을 위해 노력하고 있다. 이러한 목적을 달성하기 위하여 여러 방안들이 연구되고 있으며, 대표적으로 신뢰성 기반 유지보수(RCM; Reliability Centered Maintenance)가 철도분야에 지속적으로 도입되고 있는 추세이다. 본 연구에서는 새로운 예방정비 기술로 대두되고 있는 RCM의 기본이론에 대한 고찰과 RCM의 일반적 실시 절차를 소개하고, RCM의 국제규격인 IEC 60300-3-11, NAVAIR 00-25-403, MIL-STD-2173을 비교 분석하여 이를 바탕으로 철도차량에 RCM 도입 시 효과적이고 적합한 절차 및 방안을 제시하고자 한다.

• 한국원자력학회:학술대회논문집
• /
• 한국원자력학회 1998년도 춘계학술발표회논문집(1)
• /
• pp.838-843
• /
• 1998

Risk importance measures are widely wed to rank risk contributors in risk-based applications. Typically, Fussell-Vesely (F-V) importance and risk achievement worth (RAW) are used in the component importance raking for the reliability centered maintenance (RCM) analysis of safety system in nuclear power plants (NPPs). This study was performed as part of feasibility study on RCM for domestic NPPs, which is focused on the component importance ranking approach the maintenance recommendation. The approach of modulizing faulting tree basic events was applied in the simplification process of the PSA model and the validity of the approach was evaluated As a result of the case study, this paper included the importance and the maintenance recommendations for the safety-related equipments associated with safety injection and containment spray in large loss of coolant accident sequences.

• 한국통신학회논문지
• /
• 제31권9B호
• /
• pp.792-802
• /
• 2006

In this paper, we propose an energy-efficient proactive data dissemination protocol with relatively low delay to cope well with highly mobile sink environments in sensor networks. In order for a dissemination tree to continuously pursue a dynamic sink, we exploit two novel algorithms: forward sink advertisement and distributed fast recovery. In our protocol, the tree is shared with the other slave sinks so that we call it Dynamic Shared Tree (DST) protocol. DST can conserve considerable amount of energy despite maintaining robust connection from all sources to sinks, since tree maintenance of DST is accomplished by just distributed local exchanges. In addition, since the DST is a kindof sink-oriented tree, each source on the DST disseminates data with lower delay along the tree and it also facilitates in-network processing. Through simulations, it is shown that the presented DST is considerably energy-efficient, robust protocol with low delay compared to Directed Diffusion, TTDD, and SEAD, in highly mobile sink environment.