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

Title: Harnessing expert knowledge: Defining a Bayesian network decision model with limited data-Model structure for the vibration qualification problem

Abstract

As systems become more complex, systems engineers rely on experts to inform decisions. There are few experts and limited data in many complex new technologies. This challenges systems engineers as they strive to plan activities such as qualification in an environment where technical constraints are coupled with the traditional cost, risk, and schedule constraints. Bayesian network (BN) models provide a framework to aid systems engineers in planning qualification efforts with complex constraints by harnessing expert knowledge and incorporating technical factors. By quantifying causal factors, a BN model can provide data about the risk of implementing a decision supplemented with information on driving factors. This allows a systems engineer to make informed decisions and examine “what-if” scenarios. This paper discusses a novel process developed to define a BN model structure based primarily on expert knowledge supplemented with extremely limited data (25 data sets or less). The model was developed to aid qualification decisions—specifically to predict the suitability of six degrees of freedom (6DOF) vibration testing for qualification. The process defined the model structure with expert knowledge in an unbiased manner. Finally, validation during the process execution and of the model provided evidence the process may be an effective tool in harnessingmore » expert knowledge for a BN model.« less

Authors:
ORCiD logo [1];  [2]
  1. Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
  2. Stevens Inst. of Technology, Hoboken, NJ (United States)
Publication Date:
Research Org.:
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA)
OSTI Identifier:
1432479
Alternate Identifier(s):
OSTI ID: 1478216
Report Number(s):
SAND-2018-3223J; SAND-2017-2685J
Journal ID: ISSN 1098-1241; 661799
Grant/Contract Number:  
AC04-94AL85000; NA0003525
Resource Type:
Accepted Manuscript
Journal Name:
Systems Engineering
Additional Journal Information:
Journal Volume: 21; Journal Issue: 4; Journal ID: ISSN 1098-1241
Publisher:
Wiley
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; Bayesian network; decision model; qualification; structural knowledge assessment

Citation Formats

Rizzo, Davinia B., and Blackburn, Mark R. Harnessing expert knowledge: Defining a Bayesian network decision model with limited data-Model structure for the vibration qualification problem. United States: N. p., 2018. Web. doi:10.1002/sys.21431.
Rizzo, Davinia B., & Blackburn, Mark R. Harnessing expert knowledge: Defining a Bayesian network decision model with limited data-Model structure for the vibration qualification problem. United States. doi:10.1002/sys.21431.
Rizzo, Davinia B., and Blackburn, Mark R. Fri . "Harnessing expert knowledge: Defining a Bayesian network decision model with limited data-Model structure for the vibration qualification problem". United States. doi:10.1002/sys.21431. https://www.osti.gov/servlets/purl/1432479.
@article{osti_1432479,
title = {Harnessing expert knowledge: Defining a Bayesian network decision model with limited data-Model structure for the vibration qualification problem},
author = {Rizzo, Davinia B. and Blackburn, Mark R.},
abstractNote = {As systems become more complex, systems engineers rely on experts to inform decisions. There are few experts and limited data in many complex new technologies. This challenges systems engineers as they strive to plan activities such as qualification in an environment where technical constraints are coupled with the traditional cost, risk, and schedule constraints. Bayesian network (BN) models provide a framework to aid systems engineers in planning qualification efforts with complex constraints by harnessing expert knowledge and incorporating technical factors. By quantifying causal factors, a BN model can provide data about the risk of implementing a decision supplemented with information on driving factors. This allows a systems engineer to make informed decisions and examine “what-if” scenarios. This paper discusses a novel process developed to define a BN model structure based primarily on expert knowledge supplemented with extremely limited data (25 data sets or less). The model was developed to aid qualification decisions—specifically to predict the suitability of six degrees of freedom (6DOF) vibration testing for qualification. The process defined the model structure with expert knowledge in an unbiased manner. Finally, validation during the process execution and of the model provided evidence the process may be an effective tool in harnessing expert knowledge for a BN model.},
doi = {10.1002/sys.21431},
journal = {Systems Engineering},
number = 4,
volume = 21,
place = {United States},
year = {2018},
month = {3}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 1 work
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Decision support analysis for safety control in complex project environments based on Bayesian Networks
journal, September 2013


Use of Bayesian Networks for Qualification Planning: Early Results of Factor Analysis
journal, January 2016


From complex questionnaire and interviewing data to intelligent Bayesian network models for medical decision support
journal, February 2016

  • Constantinou, Anthony Costa; Fenton, Norman; Marsh, William
  • Artificial Intelligence in Medicine, Vol. 67
  • DOI: 10.1016/j.artmed.2016.01.002

Risk modelling of a hydrogen refuelling station using Bayesian network
journal, February 2011


Metrics for evaluating performance and uncertainty of Bayesian network models
journal, April 2012


Assessing structural knowledge.
journal, March 1991

  • Goldsmith, Timothy E.; Johnson, Peder J.; Acton, William H.
  • Journal of Educational Psychology, Vol. 83, Issue 1
  • DOI: 10.1037/0022-0663.83.1.88

A Method for Integrating Expert Knowledge When Learning Bayesian Networks From Data
journal, October 2011

  • Cano, A.; Masegosa, A. R.; Moral, S.
  • IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), Vol. 41, Issue 5
  • DOI: 10.1109/TSMCB.2011.2148197

Drawbacks of complex models in frequentist and Bayesian approaches to natural-resource management
journal, January 2009


Application of cognitive, skill-based, and affective theories of learning outcomes to new methods of training evaluation.
journal, January 1993


Good practice in Bayesian network modelling
journal, November 2012


A proposed validation framework for expert elicited Bayesian Networks
journal, January 2013


Analyzing the structure of expert knowledge
journal, January 2006


Application of a Bayesian model for the quantification of the European methodology for qualification of non-destructive testing
journal, February 2010

  • Gandossi, Luca; Simola, Kaisa; Shepherd, Barrie
  • International Journal of Pressure Vessels and Piping, Vol. 87, Issue 2-3
  • DOI: 10.1016/j.ijpvp.2009.12.002

Mapping model validation metrics to subject matter expert scores for model adequacy assessment
journal, December 2014

  • Teferra, Kirubel; Shields, Michael D.; Hapij, Adam
  • Reliability Engineering & System Safety, Vol. 132
  • DOI: 10.1016/j.ress.2014.07.010

The case for objective Bayesian analysis
journal, September 2006