Share Email Print
cover

Proceedings Paper

Building method of diagnostic model of Bayesian networks based on fault tree
Author(s): Xiao Liu; Haijun Li; Lin Li
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Fault tree (FT) is usually a reliability and security analysis and diagnoses decision model. It is also in common use that expressing fault diagnosis question with fault tree model. But it will not be changed easily if fault free model was built, and it could not accept and deal with new information easily. It is difficult to put the information which have nothing to do with equipment fault but can be used to fault diagnosis into diagnostic course. Bayesian Networks (BN) can learn and improve its network architecture and parameters at any time by way of practice accumulation, and raises the ability of fault diagnosis. The method of building BN based on FT is researched on this article, this method could break through the limitations of FT itself, make BN be more extensively applied to the domain of fault diagnosis and gains much better ability of fault analysis and diagnosis.

Paper Details

Date Published: 13 October 2008
PDF: 6 pages
Proc. SPIE 7127, Seventh International Symposium on Instrumentation and Control Technology: Sensors and Instruments, Computer Simulation, and Artificial Intelligence, 71272C (13 October 2008); doi: 10.1117/12.806736
Show Author Affiliations
Xiao Liu, YanTai Univ. (China)
Haijun Li, Naval Aeronautical Engineering Institute (China)
Lin Li, Naval Aeronautical Engineering Institute (China)


Published in SPIE Proceedings Vol. 7127:
Seventh International Symposium on Instrumentation and Control Technology: Sensors and Instruments, Computer Simulation, and Artificial Intelligence

© SPIE. Terms of Use
Back to Top