No abstract

There has been much recent interest in the reliability field in the application of proportional hazards modelling. A number of practitioners and academics have recently been advocating its use and reviewing the basic theory. The technique is, however, in the early stages of application in reliability studies, and apparently no satisfactory examples of its application to reliability data are to be found in the open literature. An implication is that the enormous potential of this approach for reliability analysis, as well as the particular shortcomings and difficulties of applying it in this field are not well understood in the reliability community as a whole. In this article we discuss the application of the method to the reliability analysis of the brake discs on British Railways high speed trains. The need for such an approach arose owing to the paucity of current reliability analysis methods for the problem in hand. The proportional hazards methodology provided an effective means of exploratory analysis and the application of the method provided an explanation for a previously unresolved discrepancy between the statistical and metallurgical analyses. As a result of its use, the effects of the underlying failure mechanism and the various design and operating variables and their interactions are better understood, and British Rail's maintenance policy has been changed accordingly. On the basis of experience of this and similar applications, the potential for application of proportional hazards modelling in reliability, and the likely benefits to be obtained, are discussed.

No abstract

No abstract

In an Industrial Reliability setting a number of modeling techniques are available which allow the incorporation of explanatory variables; for example, Proportional Hazards Modeling, Proportional Intensity Modeling and Additive Hazards Modeling. However, in many applied settings it is unclear what the form of the underlying process is, and thus which of the above modeling structures is the most appropriate, if any. In this paper we discuss the different modeling formulations with regard to such features as their appropriateness, flexibility, robustness and ease of implementation together with the author’s experience gained from application of the models to a wide selection of reliability data sets. In particular, a comparative study of the models when applied to a software reliability data set is provided.