International Journal of Reliability, Quality and Safety Engineering

Economic design approaches of control charts are commonly based on the assumption that various cost parameters values and the occurrence risk of assignable causes have to be a priori known with precision. However, in real operative contexts, such parameters can be really difficult to accurately estimate, especially considering costs arising from out-of-control conditions of the process. As consequence, pure economic design approaches can involve chart schemes with low statistical performance. To overcome such limitation, it is herein proposed a multi-objective economic-statistical design approach for an adaptive X-bar chart. In particular, such approach aims at the minimization of both the total quality related costs and the out-of-control average run length, in such a way assuring an optimal trade-off between economic and statistical performance of the related control procedure. Moreover, for a robust design approach, the mean shift is considered as a random variable. A mixed integer nonlinear constrained mathematical model is formulated to solve the treated problem, whereas the Pareto optimal frontier is described by the ε-constraint method. In order to show the employment of the proposed approach, an illustrative example is developed and the related considerations are given. Finally, some sensitivity analysis is also performed to investigate the effects of operative and costs parameters on chart parameters.

Software failure-occurrence or the fault-detection phenomenon is changed notably in an actual testing phase or an operational phase due to the changes of factors influencing the software reliability growth process. Taking into consideration of the effect of the change in software reliability growth modeling is expected to conduct more accurate software reliability assessment because it is said that such approach enables us to conduct more plausible software reliability assessment reflecting an actual testing-environment. We develop a framework for developing software hazard rate models with effect of change-point, and discuss change-point detection methods for applying our model to quantitative software reliability assessment. Additionally, we discuss an optimal software release problem for estimating optimal shipping time with the effect of the change as one of the application problems of our model in software project management. Finally, we show numerical examples for software reliability assessment and our optimal software release policy based on our change-point model by using actual data.

In this paper, we propose a non-homogeneous Poisson process (NHPP) based software reliability growth model (SRGM) in the presence of modified imperfect debugging and fault generation phenomenon. The testing team may not be able to remove a fault perfectly on observation of a failure due to the complexity of software systems and incomplete understanding of software, and the original fault may remain, or get replaced by another fault causing error generation. We have proposed an exponentially increasing fault content function and constant fault detection rate. The total fault content of the software for our proposed model increases rapidly at the beginning of the testing process. It grows gradually at the end of the testing process because of increasing efficiency of the testing team with testing time. We use the maximum likelihood estimation method to estimate the unknown parameters of the proposed model. The applicability of our proposed model and comparisons with established models in terms of goodness of fit and predictive validity have been presented using five known software failure data sets. Experimental results show that the proposed model gives a better fit to the real failure data sets and predicts the future behavior of software development more accurately than the traditional SRGMs.

A three-dimensional consecutive (r₁, r₂, r₃)-out-of-(m₁, m₂, m₃):F system was introduced by Akiba et al. [J. Qual. Mainten. Eng.11(3) (2005) 254–266]. They computed upper and lower bounds on the reliability of this system. Habib et al. [Appl. Math. Model.34 (2010) 531–538] introduced a conditional type of two-dimensional consecutive-(r, s)-out-of-(m, n):F system, where the number of failed components in the system at the moment of system failure cannot be more than 2rs. We extend this concept to three dimension and introduce a conditional three-dimensional consecutive (s, s, s)-out-of-(s, s, m):F system. It is an arrangement of ms² components like a cuboid and it fails if it contains either a cube of failed components of size (s, s, s) or 2s³ failed components. We derive an expression for the signature of this system and also obtain reliability of this system using system signature.

This paper presents an analysis of parametric survival models and compares their applications to time to event data used to validate the approximation for repeated events applying the Proportional Hazard Model (PHM) proposed in Mendes and Fard [Int. J. Reliab., Qual. Saf. Eng.19(6) (2012) 1240004.1–1240004.18]. The subjects studied do not show degrading failures, allowing the comparison between accelerated failure time models with the PHM. Results showed the applicability of the Weibull model and the versatility of the PHM not only to match the results of the parametric model, but also to allow the implementation of time-dependent covariates, resulting in superior model fit and more insightful interpretation for the covariate hazards. The paper contribution is to present the PHM as a simpler, more robust model to determine the acceleration factor for reliability testing when compared to the formidable task of fitting a parametric model for the distribution of failure. The Kaplan–Meier method may provide misleading guidance for covariate significance when time-dependent covariates are applied; however, relevant graphical screening is supplied. Notwithstanding, the PHM provides additional options to treat the repeated observations applying robust covariance correction for lack of heterogeneity in the fixed effects model or adopting the stratified model that absorbs the error using the stratification concept.