skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Validation of the thermal challenge problem using Bayesian Belief Networks.

Abstract

The thermal challenge problem has been developed at Sandia National Laboratories as a testbed for demonstrating various types of validation approaches and prediction methods. This report discusses one particular methodology to assess the validity of a computational model given experimental data. This methodology is based on Bayesian Belief Networks (BBNs) and can incorporate uncertainty in experimental measurements, in physical quantities, and model uncertainties. The approach uses the prior and posterior distributions of model output to compute a validation metric based on Bayesian hypothesis testing (a Bayes' factor). This report discusses various aspects of the BBN, specifically in the context of the thermal challenge problem. A BBN is developed for a given set of experimental data in a particular experimental configuration. The development of the BBN and the method for ''solving'' the BBN to develop the posterior distribution of model output through Monte Carlo Markov Chain sampling is discussed in detail. The use of the BBN to compute a Bayes' factor is demonstrated.

Authors:
;
Publication Date:
Research Org.:
Sandia National Laboratories
Sponsoring Org.:
USDOE
OSTI Identifier:
875636
Report Number(s):
SAND2005-5980
TRN: US200603%%264
DOE Contract Number:
AC04-94AL85000
Resource Type:
Technical Report
Country of Publication:
United States
Language:
English
Subject:
99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; VALIDATION; FORECASTING; COMPUTER CODES; CALCULATION METHODS; Bayesian statistical decision theory.; Thermal analysis.

Citation Formats

McFarland, John, and Swiler, Laura Painton. Validation of the thermal challenge problem using Bayesian Belief Networks.. United States: N. p., 2005. Web. doi:10.2172/875636.
McFarland, John, & Swiler, Laura Painton. Validation of the thermal challenge problem using Bayesian Belief Networks.. United States. doi:10.2172/875636.
McFarland, John, and Swiler, Laura Painton. Tue . "Validation of the thermal challenge problem using Bayesian Belief Networks.". United States. doi:10.2172/875636. https://www.osti.gov/servlets/purl/875636.
@article{osti_875636,
title = {Validation of the thermal challenge problem using Bayesian Belief Networks.},
author = {McFarland, John and Swiler, Laura Painton},
abstractNote = {The thermal challenge problem has been developed at Sandia National Laboratories as a testbed for demonstrating various types of validation approaches and prediction methods. This report discusses one particular methodology to assess the validity of a computational model given experimental data. This methodology is based on Bayesian Belief Networks (BBNs) and can incorporate uncertainty in experimental measurements, in physical quantities, and model uncertainties. The approach uses the prior and posterior distributions of model output to compute a validation metric based on Bayesian hypothesis testing (a Bayes' factor). This report discusses various aspects of the BBN, specifically in the context of the thermal challenge problem. A BBN is developed for a given set of experimental data in a particular experimental configuration. The development of the BBN and the method for ''solving'' the BBN to develop the posterior distribution of model output through Monte Carlo Markov Chain sampling is discussed in detail. The use of the BBN to compute a Bayes' factor is demonstrated.},
doi = {10.2172/875636},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Tue Nov 01 00:00:00 EST 2005},
month = {Tue Nov 01 00:00:00 EST 2005}
}

Technical Report:

Save / Share:
  • Within this paper, we provide a solution to the static frame validation challenge problem (see this issue) in a manner that is consistent with the guidelines provided by the Validation Challenge Workshop tasking document. The static frame problem is constructed such that variability in material properties is known to be the only source of uncertainty in the system description, but there is ignorance on the type of model that best describes this variability. Hence both types of uncertainty, aleatoric and epistemic, are present and must be addressed. Our approach is to consider a collection of competing probabilistic models for themore » material properties, and calibrate these models to the information provided; models of different levels of complexity and numerical efficiency are included in the analysis. A Bayesian formulation is used to select the optimal model from the collection, which is then used for the regulatory assessment. Lastly, bayesian credible intervals are used to provide a measure of confidence to our regulatory assessment.« less
  • Many salmonid populations of the intermountain region of North America are threatened by habitat degradation resulting from changing land-use practices. Public lands managed by the USDA Forest Service and USDI Bureau of Land Management comprise a significant portion of the remaining suitable habitat. Public land-use decisions must consider the potential effects on sensitive species. A computer-aided viability assessment model is presented which can help anticipate impacts of management actions on resident trout populations. Central to this system is a Bayesian belief network that links physical habitat characteristics directly to reproduction and survival parameters of a population viability model. Recognizing thatmore » such linkages are imprecise and knowledge is uncertain, this system provides probabilistic risk assessments of land-use impacts. Preliminary results suggest that the principal threats to population viability arise from a combination of chronic habitat degradation and increased risks of major or catastrophic disturbances.« less
  • This paper describes a method based on Bayesian belief networks (BBNs) sensor fault detection, isolation, classification, and accommodation (SFDIA). For this purpose, a BBN uses three basic types of nodes to represent the information associated with each sensor: (1) sensor-reading nodes that represent the mechanisms by which the information is communicated to the BBN, (2) sensor-status nodes that convey the status of the corresponding sensors at any given time, and (3) process-variable nodes that are a conceptual representation of the actual values of the process variables, which are unknown.
  • Recent events highlight the need for tools to anticipate threats posed by terrorists. Assessing these threats requires combining information from disparate data sources such as analytic models, simulations, historical data, sensor networks, and user judgments. These disparate data can be combined in a coherent, analytically defensible, and understandable manner using a Bayesian belief network (BBN). In this paper, we develop a BBN threat anticipatory model based on a deceptive reasoning algorithm using a network engineering process that treats the probability distributions of the BBN nodes within the broader context of the system development process.
  • Risk from an act of terrorism is a combination of the likelihood of an attack, the likelihood of success of the attack, and the consequences of the attack. The considerable epistemic uncertainty in each of these three factors can be addressed using the belief/plausibility measure of uncertainty from the Dempster/Shafer theory of evidence. The adversary determines the likelihood of the attack. The success of the attack and the consequences of the attack are determined by the security system and mitigation measures put in place by the defender. This report documents a process for evaluating risk of terrorist acts using anmore » adversary/defender model with belief/plausibility as the measure of uncertainty. Also, the adversary model is a linguistic model that applies belief/plausibility to fuzzy sets used in an approximate reasoning rule base.« less