Skip to main navigation Skip to search Skip to main content

Performance evaluation method of remaining useful life prediction based on pseudo life

  • Jun You Shi*
  • , Meng Shi
  • , Lu Wang
  • , Jin Zhong Li
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Based on analyzing existing metrics for prediction performance evaluation, features and defects of these metrics are summarized. A new performance evaluation method of remaining useful life (RUL) prediction is proposed, which can be used before the end-of-life of a product. The evaluation principle of this method is described in detail. A new evaluation metric named fluctuation coefficient of pseudo life is also proposed on the basis of related definitions. This new metric can be used in integrated evaluation for a prediction system. The detailed evaluation flow of this method is given. Finally, a case of RUL prediction for aircraft battery is given, and quantitative performance evaluation of RUL prediction is made by calculating this evaluation metric. The evaluation results show this new method is feasible and effective.

Original languageEnglish
Title of host publication2011 IEEE 18th International Conference on Industrial Engineering and Engineering Management, IE and EM 2011
Pages1118-1122
Number of pages5
EditionPART 2
DOIs
StatePublished - 2011
Event2011 IEEE 18th International Conference on Industrial Engineering and Engineering Management, IE and EM 2011 - Changchun, China
Duration: 3 Sep 20115 Sep 2011

Publication series

Name2011 IEEE 18th International Conference on Industrial Engineering and Engineering Management, IE and EM 2011
NumberPART 2

Conference

Conference2011 IEEE 18th International Conference on Industrial Engineering and Engineering Management, IE and EM 2011
Country/TerritoryChina
CityChangchun
Period3/09/115/09/11

Keywords

  • Actual value
  • RUL
  • consumption life
  • performance evaluation
  • predicted value
  • pseudo life

Fingerprint

Dive into the research topics of 'Performance evaluation method of remaining useful life prediction based on pseudo life'. Together they form a unique fingerprint.

Cite this