No abstract

No abstract

No abstract

No abstract

SUMMARY & CONCLUSIONSJust as estimates of cost and program timing are critical factors to be known and monitored during a new product development program, so too is the reliability perspective. The reliability estimate and the uncertainty of that estimate are an excellent way to provide this perspective. Moreover, it is possible to develop realistic reliability estimates at the beginning of a new product program even though hardware is not available, because a considerable amount of knowledge exists in the experience base of engineers, etc. This knowledge is elicited in the form of expert judgment. Further, during the course of the development program much information will become available at different levels of the system (e.g., component, subsystem, system), from different sources (e.g., customer, supplier), and regarding different points in product life (e.g., test time). This information will also become available at different calendar times, and it may range from completely quantitative (e.g., test data) to totally qualitative (e.g., expert judgment) information. Fortunately, it is possible to provide order to all of this diverse information so that it may be consolidated as it occurs. The results may then be used to not onIy provide a reliability perspective of the program at any point in time, but also to provide steerage to the development team with regard to how to drive reliability higher and / or reduce the uncertainty in reliability. The challenge has been to develop a framework for this perspective which is physically and mathematically sound, but which is flexible enough to accommodate all of the diverse information that becomes available, and responsive enough to provide timely results which support the development process. The information updating approach which is rooted in Bayesian statistics is suggested as a key methodology which is directly applicable to this problem. This paper describes an approach to reliability modeling that encompasses the impact of both product and manufacturing process design on the distribution (characterizing the uncertainty) of reliability over time. It further describes the elicitation of expert judgment which is used to quantify the initial reliability estimate, including uncertainty. Finally, it describes a Bayesian updating approach which is applicable throughout the development program, and which accommodates a wide variety of possible new information. Although the model is rigorous in its execution, a user friendly approximation is also described which may be useful to the product development team for purposes of test and validation planning.