International Journal of Reliability, Quality and Safety Engineering

Single Acceptance Sampling by Attributes (SASA) is a well known problem, when the proportion of defective items is constant during the inspection process. In this paper, we are interested in a more general SASA problem where the proportion of defective items is an increasing exponential function p(k, p₀, p_∞, λ) = p_∞ - (p_∞ - p₀)e^-kλ of the number k of inspected items. In order to find the sampling parameters a and n for this problem, we suggest a method using a lognormal approximation.

Software measurement and modeling is intended to improve quality by predicting quality factors, such as reliability, early in the life cycle. The field of software measurement generally assumes that attributes of software products early in the life cycle are somehow related to the amount of information in those products, and thus, are related to the quality that eventually results from the development process.

Kolmogorov complexity and information theory offer a way to quantify the amount of information in a finite object, such as a program, in a unifying framework. Based on these principles, we propose a new synthetic measure of information composed from a set of conventional primitive metrics in a module. Since not all information is equally relevant to fault-insertion, we also consider components of the overall information content. We present a model for fault-insertion based on a nonhomogeneous Poisson process and Poisson regression. This approach is attractive, because the underlying assumptions are appropriate for software quality data. This approach also gives insight into design attributes that affect fault insertion.

A validation case study of a large sample of modules from a very large telecommunications system provides empirical evidence that the components of synthetic module complexity can be useful in software quality modeling. A large telecommunications system is an example of a computer system with rigorous software quality requirements.

The Power-Law process, also known as the Duane model, is a nonhomogeneous Poisson process which is widely used in reliability growth modeling. Goodness-of-fit tests for this process have been proposed by Crow, Rigdon, Klefsjö–Kumar and Park–Kim. In this paper, we propose several new tests based on chi-square, Laplace and conditional probability integral transform (CPIT) methodologies. We show that the TTT-plot test reduces to the Laplace test with Durbin's modification. We compare the power of 15 goodness-of-fit tests for the Power-Law process, and apply them to real software reliability data.

This article is mainly to study the reliability evaluation in terms of MPs (minimal paths) for a multistate flow network G in which the capacities of each arc are real numbers. The transportation system from the source node s to the sink node t is one of such typical networks. Given the system demand d from s to t and MPs in advance, an algorithm is proposed first to find out all lower boundary points of level d (namely d-MPs here). The system reliability which is the probability that the system flow satisfies the demand d can be calculated in terms of such d-MPs. One example is presented to illustrate how all its d-MPs are generated. The computational time complexity in the worst case and average cases for such an algorithm is presented.

In this note, a pseudodynamic cost limit replacement policy presented by Park¹ is considered. Park¹ showed that the pseudodynamic policy is inferior to constant repair cost limit policy. In this note, the correct mean cost rate under the same assumption in the Park's model is obtained and the pseudodynamic policy is shown to be better than the constant repair cost limit policy² through the same numerical examples of Park.¹

The marginal cost approach has proved a useful economics-based alternative to the well known classical analysis of replacement models. In this paper, the marginal cost analysis' workings are explored for some basic ordering models for systems with a single spare unit. As with replacement models, the fundamental quantity of interest is the marginal cost function. While the basic pattern of analysis broadly corresponds to that for replacement models, the usual micro-type reasoning inherent in marginal cost analysis now has to be supplemented by some look-ahead considerations and a more detailed analysis. Moreover, the optimality equation derived here for ordering models is an extension of that for replacement models. Two kinds of objective functions are considered here: the long term expected cost rate function and the expected total discounted cost function. Several ordering policies are reviewed by way of the marginal cost approach, which, it is argued, is a viable and from the decision maker's perspective attractive tool of analysis also in the ordering context.