Prognosis of remaining useful life for complex engineering systems
- Univ. of Tennessee, Nuclear Engineering Dept., Knoxville, TN 37996-2300 (United States)
- Physical Sciences Center, Sun Microsystems, San Diego, CA 92122 (United States)
There has been a growing interest in extending conventional maintenance strategies, such as corrective and predictive maintenance, towards the implementations that would allow forecasting of system degradation through a prognostic procedure. The recent progress in sensor and computer technologies employed in complex engineering systems facilitates the integration of model-based and data-driven diagnostics and prognostics leading to condition-based maintenance and extended availability of equipment. This paper describes data-driven models and methods aimed at performing the tasks constituting the diagnostic/prognostic framework. The proposed models and methods allow performing Prognostic and Health Management (PHM) routines over a fleet of equipment populating complex engineering systems. Although several approaches to PHM implementation have been categorized in recently published literature, this paper focuses on PHM techniques associated with observing features related to anomalous system behavior. Observed anomalous patterns in the system behavior are considered to be precursors of impending failures. Measurements taken on the observed deviations are used to deduce a quantitative estimate of how long the system will stay within its specification-defined operational ranges. (authors)
- Research Organization:
- American Nuclear Society, 555 North Kensington Avenue, La Grange Park, IL 60526 (United States)
- OSTI ID:
- 22030048
- Resource Relation:
- Conference: NPIC and HMIT 2006: 5. International Topical Meeting on Nuclear Plant Instrumentation Controls, and Human Machine Interface Technology, Albuquerque, NM (United States), 12-16 Nov 2006; Other Information: Country of input: France; 18 refs.; Related Information: In: Proceedings of the 5. International Topical Meeting on Nuclear Plant Instrumentation Controls, and Human Machine Interface Technology| 1430 p.
- Country of Publication:
- United States
- Language:
- English
Similar Records
Prognostication of LED Remaining Useful Life and Color Stability in the Presence of Contamination
Implementation of Remaining Useful Lifetime Transformer Models in the Fleet-Wide Prognostic and Health Management Suite