Spectrum-Based Sequential Diagnosis

Alberto Gonzalez-Sanchez, Rui Abreu, Hans-Gerhard Gross, and Arjan J.C. van Gemund
Submission Type: 
Full Paper
AttachmentSizeTimestamp
phmc_10_091.pdf85.22 KBOctober 24, 2010 - 7:11am

Often multiple observations are required to achieve acceptable diagnostic certainty. We present a spectrum-based sequential diagnosis approach coined sequoia, that greedily selects tests out of a suite of tests to narrow down the set of diagnostic candidates with a minimum number of tests. Sequoia handles multiple faults, that can be intermittent, at polynomial time and space complexity. This is due to a novel, approximate diagnostic entropy estimation approach, which is based on a relatively small subset of diagnoses that cover almost all Bayesian posterior probability mass. Synthetic data shows, that the dynamic selection of the next best test based on the test results measured so far, allows sequoia to achieve much better decay of diagnostic uncertainty compared to random test sequencing. Real programs, taken from the Siemens set, also show that sequoia has better performance, except in a few cases where the diagnosis includes large fault sets, which affects the entropy estimation quality.

Publication Control Number: 
091
Submission Keywords: 
multiple faults
Testing
sequential diagnosis
Submitted by: 
  
 
 
 

follow us

PHM Society on Facebook Follow PHM Society on Twitter PHM Society on LinkedIn PHM Society RSS News Feed