A predictive tool for remaining useful life estimation of rotating machinery components

Haitao Liao, Hai Qiu, Jay Lee, Daming Lin, Dragan Banjevic, Andrew Jardine

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Scopus citations

Abstract

This paper introduces a model for multiple degradation features of an individual component. The maximum likelihood approach is employed to estimate the model parameters. Afterwards, a proportional hazards model is presented, which considers hard failures and multiple degradation features simultaneously. The integrated model enables us to predict the mean remaining useful life of a component based on on-line degradation information. An example for bearing prognostic is provided to demonstrate the proposed models in practical use.

Original languageEnglish (US)
Title of host publicationProc. of the ASME International Design Engineering Technical Conferences and Computers and Information in Engineering Conferences - DETC2005
Subtitle of host publication20th Biennial Conf. on Mechanical Vibration and Noise
PublisherAmerican Society of Mechanical Engineers
Pages509-515
Number of pages7
ISBN (Print)0791847381, 9780791847381
DOIs
StatePublished - 2005
Externally publishedYes
EventDETC2005: ASME International Design Engineering Technical Conferences and Computers and Information in Engineering Conference - Long Beach, CA, United States
Duration: Sep 24 2005Sep 28 2005

Publication series

NameProceedings of the ASME International Design Engineering Technical Conferences and Computers and Information in Engineering Conference - DETC2005
Volume1 A

Other

OtherDETC2005: ASME International Design Engineering Technical Conferences and Computers and Information in Engineering Conference
Country/TerritoryUnited States
CityLong Beach, CA
Period9/24/059/28/05

ASJC Scopus subject areas

  • General Engineering

Fingerprint

Dive into the research topics of 'A predictive tool for remaining useful life estimation of rotating machinery components'. Together they form a unique fingerprint.

Cite this