Bayesian methods for assessing system reliability: models and computation.
- Todd L.
There are many challenges with assessing the reliability of a system today. These challenges arise because a system may be aging and full system tests may be too expensive or can no longer be performed. Without full system testing, one must integrate (1) all science and engineering knowledge, models and simulations, (2) information and data at various levels of the system, e.g., subsystems and components and (3) information and data from similar systems, subsystems and components. The analyst must work with various data types and how the data are collected, account for measurement bias and uncertainty, deal with model and simulation uncertainty and incorporate expert knowledge. Bayesian hierarchical modeling provides a rigorous way to combine information from multiple sources and different types of information. However, an obstacle to applying Bayesian methods is the need to develop new software to analyze novel statistical models. We discuss a new statistical modeling environment, YADAS, that facilitates the development of Bayesian statistical analyses. It includes classes that help analysts specify new models, as well as classes that support the creation of new analysis algorithms. We illustrate these concepts using several examples.
- Research Organization:
- Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
- Sponsoring Organization:
- USDOE
- OSTI ID:
- 977879
- Report Number(s):
- LA-UR-04-6834; TRN: US201012%%565
- Resource Relation:
- Journal Volume: 10; Conference: Submitted to: Fourth International Conference on Mathematical Methods in Reliability, Santa Fe , NM
- Country of Publication:
- United States
- Language:
- English
Similar Records
Using discrete Bayesian networks for diagnosing and isolating cross-level faults in HVAC systems
Active Subspace Methods for Data-Intensive Inverse Problems (Final Report)