• 정보처리학회논문지D
• /
• 제10D권5호
• /
• pp.805-812
• /
• 2003

본 논문에서는 비동질 포아송 과정(NHPP)에 기초한 소프트웨어 에러 현상에 대한 신뢰도 모형을 고려하고 사전정보(Prior information)를 이용한 베이지안 추론을 시행하였다. 고장 패턴은 NHPP에 대한 강도함수와 평균값 함수로서 나타낼 수 있다. 따라서 본 논문에서는 대수형 포아송 실행시간 모형(Logarithmic Poisson model), Crow 모형 그리고 Rayleigh 모형에 대하여 베이지안 모수 추정방법을 적용하였다. 효율적 모형을 위하여 이들 모형에 관한 모형선택을 편차자승합(SSE)의 합을 이용하여 시행하였고 모수의 추정을 위해서 마코브체인 몬테카를로(MCMC) 기법중에 하나인 깁스샘플링(Gibbs sampling)과 메트로폴리스 알고리즘을 이용한 근사추정 기법이 사용되었다. 수치적인 예에서는 Musa의 T1 자료를 이용하여 모수 및 신뢰도를 추정한 수치 결과론 나열하였다.

• International Journal of Quality Innovation
• /
• 제5권1호
• /
• pp.1-9
• /
• 2004

The nonhomogeneous poisson process (NHPP) is often used to model repairable systems that are subject to a minimal repair strategy, with negligible repair times. In this situation, the system can be characterized by its intensity function. There have been many NHPP models according to intensity functions. However, the intensity function of system in use can be changed because of repair or its aging. We consider the single change point model as the modification of the power law process. The shape parameter of its intensity function is changed before and after the change point. We detect the presence of the change point using Bayesian methodology. Some numerical results are also presented.

• 디지털산업정보학회논문지
• /
• 제8권2호
• /
• pp.1-10
• /
• 2012

In this study, software products developed in the course of testing, software managers in the process of testing software test and test tools for effective learning effects perspective has been studied using the NHPP software. The finite failure nonhomogeneous Poisson process models presented and the life distribution applied exponential and log shaped type hazard function. Software error detection techniques known in advance, but influencing factors for considering the errors found automatically and learning factors, by prior experience, to find precisely the error factor setting up the testing manager are presented comparing the problem. As a result, the learning factor is greater than autonomous errors-detected factor that is generally efficient model could be confirmed. This paper, a failure data analysis of applying using time between failures and parameter estimation using maximum likelihood estimation method, after the efficiency of the data through trend analysis model selection were efficient using the mean square error and coefficient of determination.

• 정보처리학회논문지D
• /
• 제8D권4호
• /
• pp.393-400
• /
• 2001

본 논문에서는 비동질 포아송 프로세스(NHPP)에 기초한 소프트웨어 에러 현상에 대한 확률 모형을 고려하였다. 고장 패턴은 NHPP에 대한 강도함수와 평균값 함수로서 나타낼 수 있다. 따라서 본 논문에서는 기존의 모형인 Goel 이 제시한 일반화모형[2]과 Yamada, Ohba-Osaki 모형[11]을 재조명하고 이러한 모형과 연관되고 신뢰도 분포로 많이 사용되는 와이블 분포의 특수형태인 레일리(Rayleigh)분포와 겜벨(Gumbel)분포[5]를 이용한 모형을 제시하고, 또 효율적 모형을 위한 모형선택으로서 편차자승합(SSE)을 이용하여 비교하였다. 모수의 추정을 위해서 최우추정법(MLE)과 일반적인 수치해석적 방법인 이분법을 이용하였다. 수치적인 예에서는 실측자료인 NTDS 자료[4]를 이용하여 모수 및 신뢰도를 추정하였고 편차자승합을 이용한 모형비교의 결과를 나열하였다.

• 한국전자통신학회논문지
• /
• 제18권5호
• /
• pp.935-944
• /
• 2023

본 연구에서는 신뢰성 연구에 적합하다고 알려진 Inverse-type(: Inverse-Exponential, Inverse-Rayleigh) 수명분포를 유한고장 NHPP(: Nonhomogeneous Poisson Process) 기반의 소프트웨어 개발비용 모형에 적용한 후, 성능을 결정하는 속성을 분석하였다. 또한, 모형의 효율성을 평가하기 위해 Goel-Okumoto 기본 모형과 함께 비교하였다. 고장 시간 데이터를 이용하여 모형의 성능을 분석하였고, 모수의 계산은 MLE(: Maximum Likelihood Estimation)를 적용하였다. 결론적으로, 첫째, 개발비용을 결정하는 m(t)를 분석한 결과, Inverse-Exponential 모형이 참값에 대한 오차가 적어 효율적이었다. 둘째, 개발비용과 함께 방출시간을 분석한 결과 Inverse-Rayleigh 모형이 가장 좋은 것으로 확인되었다. 셋째, 제안된 모형의 속성(m(t), 비용, 방출시간)을 종합적으로 평가한 결과, Inverse-Rayleigh 모형의 성능이 가장 우수하였다. 따라서 소프트웨어 개발자가 초기 프로세스에서 본 연구 데이터를 효율적으로 활용할 수 있다면, 비용에 영향을 미치는 속성들을 사전에 탐색하고 분석할 수 있을 것이다.

• 디지털산업정보학회논문지
• /
• 제8권4호
• /
• pp.25-34
• /
• 2012

In this study, in the process of testing before the release of the software products designed, software testing manager in advance should be aware of the testing-information. Therefore, the effective learning effects perspective has been studied using the NHPP software. The finite failure nonhomogeneous Poisson process models presented and applied property of learning effect based on truncated time and delayed S-shaped software reliability. Software error detection techniques known in advance, but influencing factors for considering the errors found automatically and learning factors, by prior experience, to find precisely the error factor setting up the testing manager are presented comparing the problem. As a result, the learning factor is greater than autonomous errors-detected factor that is generally efficient model can be confirmed. This paper, a failure data analysis was performed, using time between failures, according to the small sample and large sample sizes. The parameter estimation was carried out using maximum likelihood estimation method. Model selection was performed using the mean square error and coefficient of determination, after the data efficiency from the data through trend analysis was performed.

• 품질경영학회지
• /
• 제39권2호
• /
• pp.170-178
• /
• 2011

In general, a software fault detection phenonenon is described by a software reliability model based on a nonhomogeneous Poisson process(NHPP). In this paper, we propose a software reliability growth model considering the differences of the software environments in both the testing phase and the operational phase. Also, we consider the problem of determining the optimal release time and the optimal warranty period that minimize the total expected software cost which takes account of periodic software maintenance(e.g. patch, update, etc). Finally, we analyze the sensitivity of the optimal release time and warranty period based on the fault data observed in the actual testing process.

• 품질경영학회지
• /
• 제36권1호
• /
• pp.89-95
• /
• 2008

In this paper, we propose a software reliability growth model based on the superposition cause in the software system, which is isolated by the executed test cases in software testing. In particular, our model assumes an imperfect debugging environment in which new faults are introduced in the fault-correction process, and is formulated as a nonhomogeneous Poisson process(NHPP). Further, it is applied to fault-detection data, the results of software reliability assessment are shown, and comparison of goodness-of-fit with the existing software reliability growth model is performed.

• International Journal of Reliability and Applications
• /
• 제7권2호
• /
• pp.155-166
• /
• 2006

Many software reliability growth models (SRGMs) based on nonhomogeneous Poisson process (NHPP) have been developed and applied in practice. NHPP SRGMs are characterized by their mean value functions. Mean value functions are usually derived from differential equations representing the fault detection/removal process during testing. In this paper such differential equations are regarded as frameworks for generating mean value functions. Currently available frameworks are theoretically discussed with respect to capability of representing the fault detection/removal process. Then two general frameworks are proposed.

• 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.