#01-8
In Outdoor Environments
By
Victor Chan and William Q.
Meeker
Iowa State University
ABSTRACT
Some important reliability problems involve
estimating a life distribution when failure is due to chemical degradation of
materials or products that are exposed to the outdoor environment. There is a growing need to obtain timely
predictions of such degradation behaviors on the basis of accelerated
laboratory tests. Laboratory life tests
provide information about degradation processes. Historical weather data are used to characterize the stochastic
outdoor environment over time. A
physical/chemical model for degradation rate is used as a basis for using these
data to produce reliability estimates.
We propose and illustrate the use of an evaluation/estimation method
that involves time series modeling. The
method is illustrated with an example involving the degradation of a
solar-reflector material. We will also
show how to construct approximate confidence intervals for important
reliability.