Improving Reliability Understanding Through Estimation and Prediction with Usage Information

Using information about the usage or exposure of a complex system in addition to its age can provide additional understanding about mechanisms driving change in reliability as well as potentially improve the prediction. Both the individual reliability of particular units as well as population reliability can be improved with the inclusion of additional explanatory factors. In this article we consider an example based on a complex munition system. Using age alone to predict reliability can provide some information, but differences between units of the same age cannot be discerned. Subpopulations of the stockpile can be identified to help improve estimation, but the largest gains in understanding of the mechanisms driving change in reliability and prediction of future performance come from incorporating usage information.