Search Results

This paper presents a method of accounting for sample variability and sample size in establishing the acceptable bogey levels. The technique makes use of the statistical tolerance theory which accounts for the variability of the sample mean and standard deviation by determining a K-factor adjusted for sample size. The result is a tolerance that is reasonably assumed to cover a specified fraction of the population of parts. The technique, although not as simple as a fixed bogey, does discriminate between designs with different levels of energy management robustness.

The changes in reliability of the Electrical/Electronic Systems of a vehicle-line during its early design and development engineering processes have been studied. A computerized vehicle failure tracking system was used to provide results from several stages of early development vehicle testing at the proving grounds. The data were analyzed using a software program that assumes that failures in a repairable system, such as a car, occur as a nonhomogeneous Poisson process. Results suggest that, under normal circumstances, a significant and quantitative improvement in reliability is achievable as the system or component design progresses through the early design and development processes. This also provides a means of predicting future system(s) reliability when the system(s) is in production.