• 한국산학기술학회논문지
• /
• 제22권4호
• /
• pp.611-620
• /
• 2021

정비 산업은 사후정비, 예방정비를 거쳐, 상태기반 정비를 중심으로 진행되고 있다. 상태기반 정비는 장비의 상태를 파악하여, 최적 시점에서의 정비를 수행한다. 최적의 정비 시점을 찾기 위해서는 장비의 상태, 즉 잔여 유효 수명을 정확하게 파악하는 것이 중요하다. 이에, 본 논문은 시뮬레이션 데이터(C-MAPSS)를 사용한 터보팬 엔진의 잔여 유효수명(RUL, Remaining Useful Life) 예측 모델을 제시한다. 모델링을 위해 C-MAPSS(Commercial Modular Aero-Propulsion System Simulation) 데이터를 전처리, 변환, 예측하는 과정을 거쳤다. RUL 임계값 설정, 이동평균필터 및 표준화를 통해 데이터 전처리를 수행하였고, 주성분 분석(Principal Component Analysis)과 k-NN(k-Nearest Neighbor)을 활용하여 잔여 유효 수명을 예측하였다. 최적의 성능을 도출하기 위해, 5겹 교차검증기법을 통해 최적의 주성분 개수 및 k-NN의 근접 데이터 개수를 결정하였다. 또한, 사전 예측의 유용성, 사후 예측의 부적합성을 고려한 스코어링 함수(Scoring Function)를 통해 예측 결과를 분석하였다. 마지막으로, 현재까지 제시되어온 뉴럴 네트워크 기반의 알고리즘과 예측 성능 비교 및 분석을 통해 k-NN 활용 모델의 유용성을 검증하였다.

• 전기학회논문지
• /
• 제62권6호
• /
• pp.881-885
• /
• 2013

In this paper, we present a deterioration judgment model of urban rail power equipment using driving history, the frequency and number of failures. In addition, we have developed a deterioration judgment program based on the derived failure rate. A deterioration judgment model of power equipments on metro system was designed to establish how much environmental factors, such as thermal cycling, humidity, overvoltage and partial discharge. The deterioration rate of the transformers followed the Arrhenius log life versus reciprocal Kelvin temperature (hotspot temperature) relation. The deterioration judgment program is linked to the online condition monitoring system of urban railway system. The deterioration judgment program is based on the user interface it is possible to apply immediately to the urban rail power equipment.

• 한국신뢰성학회:학술대회논문집
• /
• 한국신뢰성학회 2005년도 학술발표대회 논문집
• /
• pp.121-129
• /
• 2005

In this paper, we consider a periodic preventive maintenance(PM) policy in which each PM reduces the hazard rate of amount proportional to the failure intensity, which increases since the last PM and slows down the wear-out speed to that of new one. And the proportion of reduction in hazard rate decreases with the number of PMs. Our model is similar to $ARI_1$ proposed by Doyen and Gaudoin(2004) in the sense of reduction of hazard rate. Our model has totally different wear-out pattern of hazard rate after PM's, however, and the proportion of reduction depends on the number of PM's. Assuming that the system undergoes only minimal repairs at failures between PM's, the expected cost rate per unit time is obtained. The optimal number N of PM and the optimal period x, which minimize the expected cost rate per unit time are discussed. Explicit solutions for the optimal periodic PM are given for the Weibull distribution case.

• International Journal of Reliability and Applications
• /
• 제14권2호
• /
• pp.55-70
• /
• 2013

This paper deals with the Bayesian analysis of the failure data of a repairable mechanical system subject to minimal repairs and periodic overhauls. The effect of overhauls on the reliability of the system is modeled by a proportional age reduction model and the failure process between two successive overhauls is assumed to be 2-parameter Engelhardt-Bain process (2-EBP). Power Law Process (PLP) model has a disadvantage which 2-EBP can overcome. On the basis of the observed data and of a number of suitable prior densities, point and interval estimation of model parameters, as well as quantities of relevant interest are found. Also hypothesis tests on the effectiveness of performed overhauls have been developed using Bayes factor. Sensitivity analysis of improvement parameter is carried out. Finally, a numerical application is used to illustrate the proposed method.

• 한국건설관리학회논문집
• /
• 제21권6호
• /
• pp.46-55
• /
• 2020

도로연장의 지속적인 증가와 공용기간이 상당히 경과한 노후 노선이 늘어남에 따라 도로포장에 대한 유지관리비용은 점차 증가하고 있어, 예방적 유지관리를 통해 비용을 최소화 하는 방안에 대한 필요성이 제기되고 있다. 예방적 유지관리를 위해서는 도로포장의 정확한 파손 예측을 통한 전략적 유지관리 계획 수립이 필요하다. 이에 본 연구에서는 고속도로 콘크리트 포장 파손 예측 모델 개발을 위해 머신러닝 분류기반 모델 중 성능이 우수한 XGBoost 기법을 사용하였다. 먼저 데이터 샘플링을 통해 데이터 불균형 문제를 해결하고 샘플링된 데이터들에 XGBoost 기법을 활용하여 예측모델을 개발하고. F1 소코어를 통해 성능을 평가하였다. 분석 결과 오버 샘플링 기법이 가장 좋은 성능 결과를 보였으며, 도로파손에 영향을 주는 주요 변수로 공용년수, ESAL, 최저 평균 최저기온 -2도 이하 일수 순으로 산정되었다. 향후 더 많은 데이터 축적 및 세밀한 데이터 전처리 작업을 통해 예측모델의 성능이 향상된다면 보다 정확한 유지보수 필요 구간의 예측이 가능해질 것으로 판단되므로 장래 고속도로 포장 유지보수 예산의 추정에 중요한 기초정보로 활용될 수 있을 것이라 기대된다.

• 한국정보통신학회논문지
• /
• 제21권11호
• /
• pp.2052-2060
• /
• 2017

SOLAS 선박은 SFI group 코드 기준으로 적어도 83종의 장비를 탑재해야 하고, 각각의 장비는 다시 수 개에서 수십 개의 컴포넌트로 구성이 된다. 선박 운항 중에는 이러한 장비의 정상적인 운영이 보장되어야 하고, 문제 발생시 즉각적인 수리를 위하여 원격유지보수의 요구사항이 높다. 본 연구는 항해통신장비의 원격유지보수에 적합한 장비의 분류체계를 제시하고, 적절한 데이터베이스 구조를 도출하고자 했다. 연구 결과, 선박 항해통신장비의 원격유지보수를 위하여, 장비의 분류체계는 장비의 종류, 모델, 컴포넌트로 계층화되어야 하고, 고장모드와 영향분석, 질의응답, 수리이력, 상태정보와 예방정비 등의 테이블을 장비 모델 기준으로 구축하는 것이 효과적임을 알게 되었다. 140개의 항해통신장비 모델과 750개의 컴포넌트에 대하여 데이터베이스를 구축하였고, 실질적인 효과를 평가하기 위하여 선박장비 수리전문가가 클라우드 앱을 이용하여 검색 결과의 유용성을 평가하였다.

• 한국치위생학회지
• /
• 제9권4호
• /
• pp.620-632
• /
• 2009

Objectives : The present study purposed to survey the oral health-related quality of life among elderly in metropolis Methods : We had individual interviews and oral survey using a questionnaire with 336 elderly who were using seniors' centers in Metropolitan City during the period from the $9^{th}$ to $31^{st}$ of July, 2007. Results : Factors of GOHAI showed the significant relation with types of health insurance, a large number of medication, perceived oral health status, perception of dental care needs those with pains in the temporomandibular joint, the number of natural teeth and the explanatory power or the final model was 25.5%. Factors of OHIP-14 showed the significant relation with types of health insurance, a large number of medication, perception of dental care needs those with pains in the temporomandibular joint, gingival bleeding, the number of natural teeth and the explanatory power or the final model was 26.6%. Conclusions : Oral health-related quality of life among elderly as factors by general characteristics of study subjects, by perceived heath status and oral health status, perceived oral symptoms and oral health status that were relevant. Accordingly, for the healthy maintenance of elders' natural teeth, it is considered necessary to develop and execute continuous oral health management systems and oral health education programs that promote preventive activities and enhance the perception of oral health.

• 시스템엔지니어링학술지
• /
• 제16권1호
• /
• pp.84-97
• /
• 2020

This paper aims to develop an optimized inventory management method for safety critical Instrument and Control (I&C) components. In this regard, the paper focuses on estimating the consumption rate of I&C components using demand forecasting methods. The target component for this paper is the Foxboro SPEC-200 controller. This component was chosen because it has highest consumption rate among the safety critical I&C components in Korean OPR-1000 NPPs. Three analytical methods were chosen in order to develop the demand forecasting methods; Poisson, Generalized Linear Model (GLM) and Bootstrapping. The results show that the GLM gives better accuracy than the other analytical methods. This is because the GLM considers the maintenance level of the component by discriminating between corrective and preventive.

• 대한안전경영과학회:학술대회논문집
• /
• 대한안전경영과학회 2004년도 추계학술대회
• /
• pp.115-123
• /
• 2004

Replacement problems can be classed as either deterministic of stochastic. Deterministic problems are those in which the timing and the outcome of the replacement action are assumed to be known with certainty. Before proceeding with development of replacement models it is important to note that preventive replacement actions, that is, ones taken before equipment reaches a failed state, require two necessary conditions: (1) The total cost of the replacement must be greater after failure than before. (2) The failure rate of the equipment must be increasing. Equipment is subject to failure. On failure, one of two possible actions can be taken : repair or complete replacement of the failed equipment. In this paper, we proposed optimal overhaul, repair, replacement maintenance model with two-state.

• Preventive Nutrition and Food Science
• /
• 제16권4호
• /
• pp.364-369
• /
• 2011

Levels of carbon dioxide gas, a metabolite of microbial growth, have been reported to parallel the onset of microbial spoilage and may be used as a convenient index for a packaged food's shelf life. This study aimed to establish a kinetic model of $CO_2$ production from perishable food for the potential use for shelf life control in the food supply chain. Aerobic bacterial count and package $CO_2$ concentration were measured during the storage of seasoned pork meat at four temperatures (0, 5, 10 and $15^{\circ}C$), and their interrelationship was investigated to establish a mathematical model. The microbial growth at constant temperature was described by using model of Baranyi and Roberts. $CO_2$ production from the stored food could be explained by taking care of its yield and maintenance factors linked to the microbial growth. By establishing the temperature dependence of the microbial growth and $CO_2$ yield factor, $CO_2$ partial pressure or concentration in package headspace could be estimated to a limited extent, which is helpful for controlling the shelf life under constant and dynamic temperature conditions. Application and efficacy of the model needs to be improved with further refinement in the model.