• Journal of Applied Reliability
• /
• v.3 no.2
• /
• pp.93-101
• /
• 2003

Life time data analysis requires some time-to-failure data to an extent. Some life tests result in few or no failure. In such cases, it is difficult to access reliability with traditional life tests that record only time to failure. Furthermore, with short product development time, reliability tests must be conducted with severe time constraints. For some devices, it is possible to obtain degradation measurements over time, and these measurements may contain useful information about product reliability. This article describes degradation reliability analysis methods to do inferences and predictions about a failure-time distribution by using software. In addition, the possibility of extension to CBM (Condition Based Maintenance) is suggested as an example of applied degradation data analysis.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.1
• /
• pp.87-98
• /
• 2010

This research deals the method to assess the validity and reliability of students' evaluation for lectures. Most papers for student's evaluation have focused the procedures for controlling the external effects, but this paper is trying to answer for "How reliable is the student rating?" An empirical study shows that the evaluations in Jeonju University have the fair validity and reliability. The generalizability theory is suggested to obtain the more comprehensive results rather than Cronbach's alpha to examine internal consistency.

• The Journal of the Korea Contents Association
• /
• v.16 no.12
• /
• pp.551-561
• /
• 2016

A user influence discrimination scheme using big data from social networks is needed. In this thesis, we propose a user influence discrimination scheme considering reliability in social networks. The proposed scheme measures reliability scores through social activities and simplifies a social network by collecting only reliable users. It also derives user influence by considering direct and indirect influences that depends on network degree between users. As a result, the proposed scheme improves the expandability of the user influence. In order to show the superiority of the proposed scheme, we compare it with the existing scheme through performance evaluations in terms of reliability and user influence.

• Proceedings of the Korean Reliability Society Conference
• /
• 2006.05a
• /
• pp.371-379
• /
• 2006

자동차용 필라멘트 전구는 모든 차량의 전조등, 안개등, 후진등에 사용 되며, 특히 H1, H3, H4 제품은 가장 대중적이고 차량의 적용율이 높은 제품으로 적은 체적에서 높은 광속 효과를 얻을 수 있어 차량용 조명등에 적용되고 있다 본 글에서는 안정성 및 신뢰성이 확보되지 않은 국내 자동차용 전구 및 저가의 중국산 제품에 대해 품질이 우수한 선진제품과의 신뢰성 수명 비교 평가를 통하여 현재 국산제품의 신뢰수준을 확인하고 평가결과를 제조업체에 Feed Back 하여 자동차용 필라멘트 전구의 신뢰성향상에 기여하고자 한다.

• Journal of Applied Reliability
• /
• v.14 no.2
• /
• pp.103-107
• /
• 2014

An algorithm to get network reliability, where each link has probability of fuzzy number, is proposed. Decomposition method and fuzzy numbers arithmetic are applied to the algorithm. Pivot link is chosen one by one from start node recursively at time of decomposition, and arithmetic of fuzzy complementary numbers is included at the same time. No criteria of pivot link selection and the recursive calculation make the algorithm simple.

• Journal of Korean Society for Quality Management
• /
• v.9 no.1
• /
• pp.3-11
• /
• 1981

A stress-strength model is formulated for s of k systems consisting of identical components. We consider minimum variance unbiased (MVU) estimation of system reliability for data consisting of a random sample from the stress distribution and one from the strength distribution when the two distirubtions are Weibull with unknown scale parameters and same known shape parameter. The asymptotic distribution of MVU estimate of system reliability in the model is obtained by using the standard asymptotic properties of the maximum likelihood estimate of system reliability and establishing their equivalence. Uniformly most accurate unbiased confidence intervals are also obtained for system reliability. Empirical comparison of the two estimates for small samples is studies by Monte Carlo simulation.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2015.10a
• /
• pp.256-257
• /
• 2015

The trend of globalization and the development of the communication-Information technology not only complexified the supply chain, but also, led to the needs of the high quality of logistics service for customers. I t defines risks that can occur in truck transport under unexpected situation with Fault Tree Analysis(FTA) and calculates failure rate concerning relationship between each risks. Based on the 4 kinds of middle failure events that defined in FTA, Reliability function which is regarded about risks sequentiality and time flow is resulted in. I t is meaningful that it calculates reliability of logistics and transportation system with engineering methodology.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.35 no.3
• /
• pp.180-186
• /
• 2012

신제품 개발에 있어서 제품의 잠재적 고장모드를 줄이기 위한 설계 노력은 매우 중요하며 이를 위해서는 체계적이고 혁신적인 신뢰성프로그램을 적용하는 것이 반드시 필요하다. 기업에서 동시공학을 기초로 한 건전한 신뢰성프로그램에 포함된 주요활동으로는 DFR(Design for Reliability), 신뢰성검증 및 물리적 해석활동 등이 있으며, 이 중 DFR은 제품 개발을 지원하는 첫 번째 과학적 신뢰성활동이다. 본 연구는 브레이크패드의 신뢰성을 향상시키기 위하여 회사조직전체에서 여러 부서의 팀 구성원이 유기적으로 참여하는 DFR 프로세스를 조직하고 실행하는 전략과 기술에 대한 연구이다. 본 사례연구의 동기는 해당기업에서 DFR에 적용된 모든 도구와 기술을 통해 제품의 신뢰성을 향상시키고 동시에 글로벌시장의 잠재고객에 대하여 품질과 신뢰성에 대한 확신을 주는데 유용하게 활용하기 위함이다. 본 논문에서는 제품개발주기의 개념설계단계 부터 제품의 폐기까지의 DFR 개념 전개에 대하여 설명하고, 기술적 도구를 적용한 설계초기 단계에서의 분석사례를 제시하였다.

• Journal of the Korean Institute of Gas
• /
• v.18 no.6
• /
• pp.32-39
• /
• 2014

To ensure the reliability of the safety system so that handing large quantities of hazardous materials in chemical plant is considered basic information in chemical process design. However, the reliability of the production system may be reduced when the reliability of the safety system emphasized in order to ensure the safety of chemical process. It is necessary to balance the reliability of the production system and reliability of the safety. In this study, a quantitative risk assessment was performed by selecting the furnace process, which is widely used in the chemical plant in order to suggest a way to ensure the safety and productivity of chemical process, based on the quantitative data. Quantitative risk assessment methodology have been used directed graph analysis methodology. It is possible to evaluate the reliability of the safety system and the production system. In this study, the optimum system design requirement to improve the safety and the productivity of the furnace is two-out-of-three logic for TT and PT.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2009.03a
• /
• pp.759-767
• /
• 2009

Recently, there is a trend to introduce a reliability approach to the design of al large scale improvement of weak ground due to the uncertainty of the influence factors in the consolidation. Since the reliability analysis is not easily adopted to geotechnical engineers because of some difficulties in working up the theories, Duncan(2000) proposed a simplified method for using reliability method to goetechnical problems. In this study, the applicability of Duncan's simplified reliability approach is evaluated by comparing the traditional reliability results with Duncan's. In the sensitivity analysis, the two results were quite similar. However, the probability of failure showed an error range of 20~50% and further Duncan's approach could not make a distinction for the distribution of geotechnical random variables. The simplified reliability method seems to be used properly in preliminary design if it is used supplementary with the deterministic method.