441 – Integrating Complex Reliability Data in the Real World
Bayesian Nonparametric Models for Combining Heterogeneous Reliability Data
Sponsor: Section on Physical and Engineering Sciences
Keywords: Dirichlet Process, Hierarchical Modeling, Lifetime Prediction, Parallel and Series Systems
David H. Collins
Los Alamos National Laboratory
Richard L. Warr
Air Force Institute of Technology
Modern complex engineering systems often present the analyst with a mix of data types that can be used for reliability prediction: system test results, lifetime data from unit tests of components, and subsystems data, all of which may have predictive value for the system lifetime. We present a hierarchical nonparametric framework, using Dirichlet processes, in which time-to-event distributions may be estimated from sample data or derived based on physical failure mechanisms. By applying a Bayesian methodology, the framework can incorporate prior information, including expert opinion.
