DocumentCode :
2543461
Title :
Prognosis of faults in gas turbine engines
Author :
Brotherton, Tom ; Jahns, Gary ; Jacobs, Jerry ; Wroblewski, Dariusz
Author_Institution :
Intelligent Autom. Corp., San Diego, CA, USA
Volume :
6
fYear :
2000
fDate :
2000
Firstpage :
163
Abstract :
A problem of interest to aircraft engine maintainers is the automatic detection, classification, and prediction (or prognosis) of potential critical component failures in gas turbine engines. Automatic monitoring offers the promise of substantially reducing the cost of repair and replacement of defective parts, and may even result in saving lives. Current processing for prognostic health monitoring (PHM) uses relatively simple metrics or features and rules to measure and characterize changes in sensor data. An alternative solution is to use neural nets coupled with appropriate feature extractors. We have developed techniques that couple neural nets with automated rule extractors to form systems that have: good statistical performance; easy system explanation and validation; potential new data insights and new rule discovery, novelty detection; and real-time performance. We apply these techniques to data sets data collected from operating engines. Prognostic examples using the integrated system are shown and compared with current PHM system performance. Rules for performing the prognostics will be developed and the rule performance compared
Keywords :
aerospace computing; aerospace engines; automatic testing; data mining; diagnostic expert systems; fault location; feature extraction; gas turbines; neural nets; statistical analysis; TREPAN; automated rule extractors; automatic detection; automatic monitoring; classification; cost of repair; critical component failures; data mining; defective parts; engine maintainers; exhaustive search; feature extractors; fuzzy logic; gas turbine engines; integrated prognosis; prediction; prognostic health monitoring; rule extraction; statistical performance; training data; Aircraft propulsion; Computerized monitoring; Condition monitoring; Costs; Current measurement; Data mining; Engines; Neural networks; Prognostics and health management; Turbines;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Aerospace Conference Proceedings, 2000 IEEE
Conference_Location :
Big Sky, MT
ISSN :
1095-323X
Print_ISBN :
0-7803-5846-5
Type :
conf
DOI :
10.1109/AERO.2000.877892
Filename :
877892
Link To Document :
بازگشت