• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.11a
• /
• pp.224-226
• /
• 2022

다양한 소스로부터 수집되고 연동되는 데이터를 모델링하는 기술로 그래프 데이터베이스를 활용한 분석 기법이 각광받고 있다. 이 연구에서는 항로표지에서 관측되는 상태 및 주변 정보를 모델링하고, 고장진단 및 예측에 적용할 수 있는 기계학습 기법을 소개한다.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2021.11a
• /
• pp.54-56
• /
• 2021

다양한 소스로부터 수집되고 연동되는 데이터를 모델링하는 기술로 그래프 데이터베이스를 활용한 분석 기법이 각광받고 있다. 이 연구에서는 항로표지에서 관측되는 상태 및 주변 정보를 모델링하고, 고장진단 및 예측에 적용할 수 있는 기계학습 기법을 소개한다.

• Journal of Korea Ship Safrty Technology Authority
• /
• s.26
• /
• pp.24-35
• /
• 2009

본 연구에서는 소형선박용 고속디젤기관의 고장으로 발생되는 해양사고를 저감하기 위하여 엔진의 상태를 사전에 기관운전자가 알 수 있도록 시스템을 구성하여 기존의 엔진에 이상이 발생하였을때 가시가청 경보를 울리는 것보다 한 단계 전에 엔진의 상태를 미리 알 수 있도록 하여, 기관의 고장으로 인한 해양사고 저감에 목표를 두고 과제를 진행하였다. 또한, 대형선박에서 사용하고 있는 고가의 고성능을 발휘하는 고장예측진단시스템은 많이 개발되어 있으나, 영세한 소형어선에 적용할 수 있는 소형의 저렴한 시스템 개발에 최종목표를 두고 1차년도 연구과제를 수행하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.405-407
• /
• 2016

최근, ICT/loT 기술과의 융합은 다양한 산업분야에 적용되고 있으며, 안정적인 전력공급 및 지능형전력망 구축에 대해 다양한 연구가 이루어지고 있다. 특히, 수요라인과 직접적으로 연관된 배전계통의 효율적인 운영 및 배전설비의 유지/관리 기술에 대한 연구에 많은 연구를 수행하고 있다. 본 논문에서는 다양한 배전설비에 대한 환경정보를 loT 센서를 통해 수집함으로써 실시간으로 정전상황을 불러올 수 있는 기자재의 고장감지 및 예측을 위한 시스템 모델을 제안한다. 제안하는 시스템 모델은 실시간으로 수집되는 정보들에 대해 시계열 기반의 필터링 및 이상점 판단을 위한 성분 분석을 실시하고, 고장진단 및 예측을 위해 기계학습 기반의 데이터 분석실시하여 기자재들의 고장감지 및 고장 발생 여부를 예측한다.

• Journal of the Korean Data and Information Science Society
• /
• v.8 no.1
• /
• pp.21-30
• /
• 1997

In accelerated life tests, the failure time of an item is observed under a high stress level, and based on the time the performances of items are investigated at the normal stress level. In this paper, when the mean of the prior of a failure rate is known in the exponential lifetime distribution with censored accelerated failure time data, we utilize the empirical Bayesian method by using the moment estimators in order to estimate the parameters of the prior distribution and obtain the empirical Bayesian predictive density and predictive intervals for a future observation under the normal stress level.

• Journal of Platform Technology
• /
• v.6 no.2
• /
• pp.19-25
• /
• 2018

Existing Photovoltaic(PV) monitoring system monitors the current, past power generation, all values of environmental sensors. It is necessary to predict solar power generation for efficient operation and maintenance on the power plant. We propose a method for estimating the generation of PV data based PV monitoring system with data accumulation. Through this, we intend to find the failure prediction of the photovoltaic power plant in proportion to the predicted power generation. As a result, the administrator can predict the failure of the system it will be prepared in advance.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.6
• /
• pp.1346-1352
• /
• 2009

Warranty cost of automobile parts varies depending on the parts failure rate in a warranty region of individual markets. Parts failure rate is significantly affected by usage-rate given that other stressors of individual markets are similar. Accordingly, warranty cost can be predicted by failure modeling which reflects usage-rate and using a stochastic process. In this paper, one-dimensional approach is used by applying accelerated failure time model on the assumption that the usage-rate is linear. Such model can explain changes in parts failure rate depending on the changes in usage-rate since it can be expressed as a function of usage-rate. Therefore, acquisition of usage-rate in a new market will automatically lead to estimate of failure rate even without warranty data and warranty cost of parts can be predicted through a renewal process in replacement cases. A case study using warranty data of two real markets is presented in the application part of this paper.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.21 no.6
• /
• pp.618-629
• /
• 2001

This paper presents a result of failure analysis and reliability evaluation for high voltage ceramic capacitors. The failure modes and failure mechanisms were studied in two ways in order to estimate component life and failure rate. The causes of failure mechanisms for zero resistance phenomena under withstanding voltage test in high voltage ceramic capacitors molded by epoxy resin were studied by establishing an effective root cause failure analysis. Particular emphasis was placed on breakdown phenomena at the ceramic-epoxy interface. The validity of the results in this study was confirmed by the results of accelerated testing. Thermal cycling test for high voltage ceramic capacitor mounted on a magnetron were implemented. Delamination between ceramic and epoxy, which might cause electrical short in underlying circuitry, can occur during curing or thermal cycle. The results can be conveniently used to quickly identify defective lots, determine $B_{10}$ life estimation each lot at the level of inspection, and detect major changes in the vendors processes. Also, the condition for dielectric breakdown was investigated for the estimation of failure rate with load-strength interference model.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 1994.06a
• /
• pp.13-16
• /
• 1994

• Journal of IKEEE
• /
• v.23 no.1
• /
• pp.254-260
• /
• 2019

The failure rate of bidirectional dc-to-dc converter is predicted through the failure mode and effect analysis (FMEA) and the fault-tree analysis (FTA) considering the operational risk. In order to increase the driving voltage of the electric vehicle efficiently, the bidirectional converter is attached to the front of the inverter. It has a boost mode for discharging battery power to the dc-link capacitor and a buck mode for charging the regenerative power to the battery. Based on the results of the FMEA considering the operating characteristics of the bidirectional converter, the fault-tree is designed considering the risk of the converter. After setting the design parameters for the MCU for the electric vehicle, we analyze the failure rate of the capacitor due to the output voltage ripple and the inductor component failure rate due to the inductor current ripple. In addition, we obtain the failure rate of major parts according to operating temperature using MIL-HDBK-217F. Finally, the failure rate and the mean time between failures (MTBF) of the converter are predicted by reflecting the part failure rate to the basic event of the fault-tree.