NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
Developing Large-Scale Bayesian Networks by Composition: Fault Diagnosis of Electrical Power Systems in Aircraft and SpacecraftIn this paper, we investigate the use of Bayesian networks to construct large-scale diagnostic systems. In particular, we consider the development of large-scale Bayesian networks by composition. This compositional approach reflects how (often redundant) subsystems are architected to form systems such as electrical power systems. We develop high-level specifications, Bayesian networks, clique trees, and arithmetic circuits representing 24 different electrical power systems. The largest among these 24 Bayesian networks contains over 1,000 random variables. Another BN represents the real-world electrical power system ADAPT, which is representative of electrical power systems deployed in aerospace vehicles. In addition to demonstrating the scalability of the compositional approach, we briefly report on experimental results from the diagnostic competition DXC, where the ProADAPT team, using techniques discussed here, obtained the highest scores in both Tier 1 (among 9 international competitors) and Tier 2 (among 6 international competitors) of the industrial track. While we consider diagnosis of power systems specifically, we believe this work is relevant to other system health management problems, in particular in dependable systems such as aircraft and spacecraft. (See CASI ID 20100021910 for supplemental data disk.)
Document ID
20100021404
Document Type
Conference Paper
Authors
Mengshoel, Ole Jakob (Carnegie-Mellon Univ. Pittsburgh, PA, United States)
Poll, Scott (NASA Ames Research Center Moffett Field, CA, United States)
Kurtoglu, Tolga (Mission Critical Technologies, Inc. Moffett Field, CA, United States)
Date Acquired
August 24, 2013
Publication Date
July 11, 2009
Subject Category
Aircraft Propulsion and Power
Report/Patent Number
ARC-E-DAA-TN697
Meeting Information
Twenty-first International Joint Conference on Artificial(Pasadena, CA)
Funding Number(s)
CONTRACT_GRANT: NNX08AY50A
Distribution Limits
Public
Copyright
Public Use Permitted.

Available Downloads

NameType 20100021404.pdf STI

Related Records

IDRelationTitle20100021910Supplemented ByDeveloping Large-Scale Bayesian Networks by Composition: Fault Diagnosis of Electrical Power Systems in Aircraft and Spacecraft20100021910See AlsoDeveloping Large-Scale Bayesian Networks by Composition: Fault Diagnosis of Electrical Power Systems in Aircraft and Spacecraft