Learning envelopes for fault detection and state summarization

Author

DeCoste, Dennis

Author_Institution

Jet Propulsion Lab., California Inst. of Technol., Pasadena, CA, USA

Volume

6

fYear

2000

fDate

2000

Firstpage

337

Abstract

This paper discusses a data mining approach for overcoming common problems with the traditional red-line limit-checking approach to fault detection and state summarization. It essentially involves learning and adapting parametric functions which provide context-sensitive bounds on historic time-series engineering data. Such bounds are suitable as dynamic plug-in replacements for static red-line values. They enable significantly earlier detection while maintaining low false alarm rates. An example is discussed from onboard tests of this technology during the NASA Deep Space 1 (DS1) mission

Keywords

aerospace computing; data mining; fault diagnosis; learning (artificial intelligence); probability; state estimation; DS1 mission; NASA Deep Space 1 mission; bounds estimation; context-sensitive bounds; data mining; dynamic plug-in replacements; extreme value theory; false alarm rates; fault detection; onboard tests; parametric functions; probability; red-line limit-checking; static red-line values; time-series engineering data; Data mining; Fault detection; Laboratories; Learning systems; Machine learning; Maintenance engineering; Monitoring; Propulsion; Space technology; Space vehicles;

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.2000.877908

Filename

877908