• The Korean Journal of Applied Statistics
• /
• v.8 no.2
• /
• pp.133-145
• /
• 1995

This paper is concerned with the method of estimating lifetime distribution from field data for repairable products with multiple modes of failure, and is an extension of Bai et al.(1995). The log linear function is considered as a model for describing the relation between failure time of a product and covariates. Using the nonhomogeneous poisson process, general methods for obtaining pseudo maximum likelihood estimators(PMLEs) for the parameters are outlined and specific formulas for Weibull distribution are obtained. Effects of follow-up percentage on the PMLEs are investigated. Extension to case-cohort design is also considered.

• The KIPS Transactions:PartC
• /
• v.8C no.2
• /
• pp.182-188
• /
• 2001

이동 호스트에서 기지국으로의 데이터 전송 시 예상치 못한 기지국 전체 고장은 필연적으로 버퍼에 있는 데이터의 손실을 초래하고 적절한 손실 보상이 필요하다. 기지국의 고장시의 회복을 위한 기존의 기법들은 오버헤드가 많고 단순히 무선 링크 장애만을 고려하므로 기지 국 전체 고장에는 적합하지 않다. 유무선망 전체의 신뢰성 있는 전송을 위한 End to End 전송 방식도 비효율적으로 이동 호스트가 보상할 데이터 량을 알기 위해 필요한 기지국 버 퍼의 정확한 손실 정도를 알기 어렵다. 본 논문에서는 기존에 제안된 기법들의 문제점을 분 석하고 무선 ATM망에서 기지국 고장 시에 효율적으로 손실 보상을 하도록 하는 기법으로 CPS(Checkpoint Scheme)을 제안한다. CPS는 기지국이 버퍼의 출력 정보를 통보하여 고장 시에 이동 호스트가 seamless한 전송을 할 수 있도록 한다. 기존의 기법들과 시뮬레이션 및 비교 분석을 통하여 CPS의 효율을 증명한다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.7 no.3
• /
• pp.393-397
• /
• 2006

The study about Accelerated Life Test and analysis of failed data is increased in order to predict and evaluate reliability of products, according as the development cycle of products is reduced. Therefore, the decision of optimal distribution function about failed data for accurate analysis of failed data and test condition for Accelerated Life Test is very important. This paper compares Anderson-Darling method with Likelihood Function method for the decision of optimal distribution function about failed data. Anderson-Darling considers only failed data and Likelihood Function considers both failed data and life-stress relationship in decision of distribution function. In the results of comparison about two methods, we found that the distribution function chosen by each method is different and the life time predicted by each decided distribution function is different.

• Proceedings of the KIEE Conference
• /
• summer
• /
• pp.21-23
• /
• 2004

전력 에너지는 안정하고 신뢰할 수 있도록 고장에 대한 빠른 대처가 필요하다. 고장시 빠른 수리를 위해서는 보수 승무원에게 고장 위치를 정확하게 알려주어 올바른 위치에 도착할 수 있도록 고장점 표정 알고리즘의 정확도가 요구된다. 본 논문에서는 기존 1회선 분기점을 갖는 병행 2회선 송전선로의 고장점 표정 알고리즘을 이용하여 정확한 고장 위치를 찾는 방법으로 개선된 NVP(N-version programming) 모델을 적용한 새로운 계산 방법을 제안한다. 송전선로의 고장 데이터는 EMTP(Electro Magnetic Transients Program)을 사용하여 154[kV], 25[km] 분기된, 병행 2회선 송전선로에서 고장지진과 고장저항의 데이터존 이용하여 시뮬레이션했다.

• The Journal of the Korea Contents Association
• /
• v.17 no.7
• /
• pp.182-192
• /
• 2017

Recently, there is an increasing interest in analysis of big data that is coming from manufacturing industry. In this paper, we use PCB (Printed Circuit Board) manufacturing data to provide manufacturers with information on areas with high PCB defect rates, and to visualize them to facilitate production and quality control. We use the K-means and DBSCAN clustering algorithms to derive the high fraction of PCB defects, and compare which of the two algorithms provides more accurate results. Finally, we develop a system of MVC structure to visualize the information about bad clusters obtained through clustering, and visualize the defected areas on actual PCB images.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.5
• /
• pp.661-666
• /
• 2002

We need the flexible method for communication network configuration and fault management business procedure. Therefore development of systematic integrating fault management system is essential to meet on these requests. We must design the integrating fault management system so that can run the repair processing for both data communication network management and new next generation data communication network of various type. In general it is effective that the system is consisted of decentralized module to be accessibele for business logic and datum to remote area. To Solve these problem, a method is to use object-oriented design technique. That is, it is to abstract reusability objects and make component module using the abstracted objects. In this paper, we propose a fault management system of communication network service using object-oriented design techniques which are UML(Unified Modeling Language) and EJB(Enterprise Java Bean).

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.8
• /
• pp.64-70
• /
• 2018

The development of weapon systems (or components) is hindered by the number of tests due to the limited development period and cost, which reduces the scale of accumulated data related to failures. Nevertheless, because a large amount of failure data and maintenance details during the operational period are managed by computerized data, the cause of failure of weapon systems (or components) can be analyzed using the data. On the other hand, analyzing the failure and maintenance details of various weapon systems is difficult because of the variation among groups and companies, and details of the cause of failure are described as unstructured text data. Fortunately, the recent developments of big data processing technology, machine learning algorithm, and improved HW computation ability have supported major research into various methods for processing the above unstructured data. In this paper, unstructured data related to the failure / maintenance of defense weapon systems (or components) is presented by applying doc2vec, a machine learning technique, to analyze the failure cases.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.11a
• /
• pp.106-109
• /
• 2005

산업화와 더불어 자동화의 요구에 따라 여러 분야에서 유도전동기의 응용 사례가 늘어나고 있다. 본 연구는 인버터단의 전류센서에서 실시간 얻어진 전류신호로 부터 대표적인 전기, 기계적인 4가지 고장(Bearing Fault, Broken Rotor bar, Misalignment, Unbalance)을 검출하여 예기치 못한 고장에 대비할 수 있는 실시간 진단 알고리듬을 제시한다. 실시간 진단의 핵심요소인 동기화 방법으로서 Hilbert Transform을 응용하였다. 총 40세트의 정상 모터 데이터를 임의로 선택하여 두 데이터의 차를 이용하여 0에 근사한 정상 모터 뎀플릿 값을 설정하였다. 이를 이용하여 진단 대상 전동기의 고장 유무를 미리 판단하게 된다. 만약 기준치 이상의 오차가 나타나게 되면, 이와 비교하기 위한 미리 수집된 각4가지 고장 전동기의 미소신호 템플릿 데이터와의 유사성을 비교하여 고장의 종류를 표시하며, 고장의 종류가 진단되지 않은 대상은 고장 유무만 표시된다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.6
• /
• pp.1-10
• /
• 2023

The nuclear power plant(NPP)'s Instrumentation and Control(I&C) system periodically conducts integrity checks for the maintenance of self-diagnostic function during normal operation. Additionally, it performs functionality and performance checks during planned preventive maintenance periods. However, there is a need for technological development to diagnose failures and prevent accidents in advance. In this paper, we studied methods for estimating the reliability function by utilizing environmental data and self-diagnostic data of the I&C equipment. To obtain failure data, we assumed probability distributions for component features of the I&C equipment and generated virtual failure data. Using this failure data, we estimated the reliability function using representative artificial intelligence(AI) models used in survival analysis(DeepSurve, DeepHit). And we also estimated the reliability function through the Cox regression model of the traditional semi-parametric method. We confirmed the feasibility through the residual lifetime calculations based on environmental and diagnostic data.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.34 no.6
• /
• pp.781-787
• /
• 2010

Forecasting possible failure characteristics is very important in maintenance planning because it helps in predicting any future failures and determining the optimum replacement interval. This paper examines the time.to-failure distribution of the transfer gearbox of a J79 engine by using a probability plotting technique which is one of the most convenient techniques for reliability analysis. Various probability distributions are evaluated for determining the suitable probability distribution of the failure data of the transfer gearbox, and the resulting correlation coefficient indicates that failure data have a lognormal distribution. The expected number of unscheduled maintenance actions and the optimum replacement interval for various values of cost ratios are determined.