• 정보처리학회논문지D
• /
• 제10D권5호
• /
• pp.829-836
• /
• 2003

소프트웨어 신뢰도 성장 모델은 다양하게 연구되어져 있다. 그러나 이러한 모델에서 정확한 모수를 측정하는 것은 그리 쉽지 않다. 특히 고장 데이터에 대하여 소프트웨어 신뢰도 성장 모델의 추정이 정확히 이루어져야만 모델을 설명하는 모수의 추정도 정확하게 이루어질 수 있다. 이러한 측면에서 테스팅을 통해서 얻어진 소프트웨어의 고장 데이터의 정규확률점수를 구해서 두 개의 값에 대한 플롯을 그려보고 그려진 결과를 이용해서 분포를 예측하여 예측된 분포에 적합한 소프트웨어 신뢰도 성장 모델을 적용한다면 상당히 정확한 테스팅 결과론 얻을 수 있을 것이다. 본 논문에서는 고장 테이터의 플롯을 통한 결과를 통해서 분포를 예측하고 모델을 성능평가 척도에 따라서 모의실험을 하여 그 결과를 통해서 소프트웨어 신뢰도 성장 모델의 적합성을 검정하는 연구이다. 연구결과 고장데이터의 정규점수를 이용한 플롯을 보고 소프트웨어 신뢰도 성장 모델을 예측할 수 있었고 이러한 예측을 통해서 모델 선정한다면 모델의 성능평가에서도 우수함을 확인할 수 있다.

• Journal of the Korean Data and Information Science Society
• /
• 제19권4호
• /
• pp.1361-1369
• /
• 2008

The analysis of software reliability model provides the means to analysts, software engineers, and systems analysts and developers who want to predict, estimate, and measure failure rate of occurrences in software. In this paper, reliability growth model, in which the operating time between successive failure is a continuous random variable, is proposed. This model is based on order statistics of two parameters Burr type XII distribution. We propose the measure based on U-plot. Also the performance of the suggested model is tested on real data set.

• Journal of the Korean Data and Information Science Society
• /
• 제23권4호
• /
• pp.815-823
• /
• 2012

In this paper reliability growth model in which the operating time between successive failure is a continuous random variable is proposed. This model is for Burr type XII distribution with two parameters which is discussed in two versions: the order statistics and non-homogeneous Poisson process. The two software reliability measures are obtained. The performance for two versions of the suggested model is tested on real data set by U-plot and Y-plot using Kolmogorov distance.

• 한국조명전기설비학회:학술대회논문집
• /
• 한국조명전기설비학회 2007년도 춘계학술대회 논문집
• /
• pp.366-368
• /
• 2007

In this paper, the Time-varying Failure Rate (TFR) of power distribution system equipment is extracted from the recorded failure data of Korea Electric Power Corporation (KEPCO). For TFR extraction, it is used that the fault data accumulated by KEPCO during 10 years. The TFR is approximated to bathtub curve using the exponential (random failure) and Weibull (aging failure) distribution function. In addition, Kaplan-Meier estimation is applied to TFR extraction because of incomplete failure data of KEPCO. Finally, Probability plot and regression analysis is applied. It is presented that the extracted TFR is more effective and useful than Mean Failure Rate (MFR) through the comparison between TFR and MFR.

• International Journal of Reliability and Applications
• /
• 제3권1호
• /
• pp.51-60
• /
• 2002

This paper presents the methodology for obtaining point and interval estimating of the parameters of a new two-parameter distribution with multiple-censored and singly censored data (Type-I censoring or Type-II censoring) as well as complete data, using the maximum likelihood method. The basis is the likelihood expression for multiple-censored data. Furthermore, this model can be extended to a three-parameter distribution that is added a scale parameter. Then, the parameter estimation can be obtained by the graphical estimation on probability plot.

• 대한전기학회논문지:전력기술부문A
• /
• 제54권11호
• /
• pp.548-556
• /
• 2005

Reliability evaluation of power distribution system is very important to both power utilities and customers. It present the probabilistic number and duration of interruption such as failure rate, SATDI, SAIFI, and CAIDI. However, it has a fatal weakness at reliability index because of accuracy of failure rate. In this paper, the Time-varying Failure Rate(TFR) of power distribution system equipment is extracted from the recorded failure data of KEPCO(Korea Electric Power Corporation) in Korea. For TFR extraction, it is used that the fault data accumulated by KEPCO during 10 years. The TFR is approximated to bathtub curve using the exponential(random failure) and Weibull(aging failure) distribution function. In addition, Kaplan-Meier estimation is applied to TFR extraction because of incomplete failure data of KEPCO. Finally, Probability plot and regression analysis is applied. It is presented that the extracted TFR is more effective and useful than Mean Failure Rate(MfR) through the comparison between TFR and MFR

• 한국군사과학기술학회지
• /
• 제9권2호
• /
• pp.51-59
• /
• 2006

The purpose of this paper is to present reliability analysis procedures for repairable systems and apply the procedures for assessing the reliabilities of two subsystems of a specific group of military equipment based on field failure data. The mean cumulative function, M(t), the average repair rate, ARR(t), and analytic test methods are used to determine whether a failure process follows a renewal or non-renewal process. For subsystem A, the failure process turns out to follow a homogeneous Poisson process, and subsequently, its mean time between failures, availability, and the necessary number of spares are estimated. For subsystem B, the corresponding M(t) plot shows an increasing trend, indicating that its failure process follows a non-renewal process. Therefore, its M(t) is modeled as a power function of t, and a preventive maintenance policy is proposed based on the annual mean repair cost.

• Steel and Composite Structures
• /
• 제51권4호
• /
• pp.351-361
• /
• 2024

Accurate measurement of K_IC values for gas pipeline steels is important for assessing pipe safety using failure assessment diagrams. As direct measurement of K_IC was impossible for the API X70 pipeline steel, multi-specimen fracture tests were conducted to measure J_IC using three-point bend geometry. The J values were calculated from load-displacement (F-δ) plots, and the associated crack extensions were measured from the fracture surface of test specimens. Valid data points were found for the constructed J-Δa plot resulting in J_IC=356kN/m. More data points were added analytically to the J-Δa plot to increase the number of data points without performing additional experiments for different J-Δa zones where test data was unavailable. Consequently, displacement (δ) and crack-growth (Δa) from multi-specimen tests (with small displacements) were used simultaneously, resulting in the variation of Δa-δ (crack growth law) and δ-Δa obtained for this steel. For new Δa values, corresponding δ values were first calculated from δ-Δa. Then, corresponding J values for the obtained δ values were calculated from the area under the F-δ record of a full-fractured specimen (with large displacement). Given Δa and J values for new data points, the developed J-Δa plot with extra data points yielded a satisfactory estimation of J_IC=345kN/m with only a -3.1% error. This is promising and showed that the developed technique could ease the estimation of J_IC significantly and reduce the time and cost of expensive extra fracture toughness tests.

• 한국IT서비스학회지
• /
• 제20권3호
• /
• pp.1-12
• /
• 2021

Reactor Coolant Pump (RCP) is core part of nuclear power plant to provide the forced circulation of reactor coolant for the removal of core heat. Properly monitoring vibration of RCP is a key activity of a successful predictive maintenance and can lead to a decrease in failure, optimization of machine performance, and a reduction of repair and maintenance costs. Here, we developed real-time RCP Vibration Analysis System (VAS) that web based platform using NoSQL DB (Mongo DB) to handle vibration data of RCP. In this paper, we explain how to implement digital signal process of vibration data from time domain to frequency domain using Fast Fourier transform and how to design NoSQL DB structure, how to implement web service using Java spring framework, JavaScript, High-Chart. We have implement various plot according to standard of the American Society of Mechanical Engineers (ASME) and it can show on web browser based on HTML 5. This data analysis platform shows a upgraded method to real-time analyze vibration data and easily uses without specialist. Furthermore to get better precision we have plan apply to additional machine learning technology.

• 한국정보전자통신기술학회논문지
• /
• 제11권6호
• /
• pp.645-650
• /
• 2018

소프트웨어 안정성은 운영 환경에서 시간의 흐름에 따른 오작동이 없이 운영 될 수있는 가능성이라고 할 수 있다. 소프트웨어의 고장 분석을 위한 유한 고장 NHPP에서, 고장 발생률은 일정하거나 단조롭게 증가하거나 단조 감소하는 추이를 나타낼 수 있다. 본 연구에서는 NHPP 모형에 근거하고 소프트웨어 고장시간 자료를 바탕으로 와이블 분포의 형상모수를 고려한 지수분포 Rayleigh 분포, 역-지수 분포를 수명분포로 하여 소프트웨어 개발 비용모형에 관한 속성을 비교 평가분석을 하였다. 또한 모수 추정은 최우 추정방법을 적용하고 데이터 추세검정은 박스-플롯방법을 이용하였다. 본 연구의 결과는 Rayleigh 모형이 역-지수 모형이나 Goel-Okumoto 모형에 비교해서 방출 시기는 Rayleigh 모형이 가장 빠르고 방출시점의 비용도 가장 경제적임을 알 수 있다. 이 연구의 결과를 이용하면 소프트웨어 개발자 및 운용자들은 최적방출시간과 경제적인 개발비용을 예측 하는데 활용 할 수 있으리라 판단된다.