Prognostics of machine condition using energy based monitoring index and computational intelligence

B. Samanta, C. Nataraj

Research output: Contribution to book or proceedingConference articlepeer-review

1 Scopus citations

Abstract

A procedure is presented for monitoring and prognostics of machine conditions using computational intelligence (Cl) techniques. The machine condition is assessed through an energy-based feature, termed as energy index', extracted from the vibration signals. The progression of the monitoring index' is predicted using Cl techniques, namely, recursive neural network (RNN), adaptive neuro-fuzzy inference system (ANFIS) and support vector regression (SVR). The proposed prediction procedures have been evaluated through benchmark datasets. The prognostic effectiveness of the techniques has been illustrated through vibration dataset of a helicopter drivetrain system gearbox. The performance of SVR was found to be better than RNN and ANFIS for the dataset used. The results are helpful in understanding the relationship of machine conditions, the corresponding indicating feature, the level of damage/degradation and their progression.

Original languageEnglish
Title of host publication2008 Proceedings of the ASME International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, DETC 2008
Pages1347-1358
Number of pages12
EditionPART B
StatePublished - 2009
Event2008 ASME International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, DETC 2008 - New York City, NY, United States
Duration: Aug 3 2008Aug 6 2008

Publication series

Name2008 Proceedings of the ASME International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, DETC 2008
NumberPART B
Volume3

Conference

Conference2008 ASME International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, DETC 2008
Country/TerritoryUnited States
CityNew York City, NY
Period08/3/0808/6/08

Scopus Subject Areas

  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Industrial and Manufacturing Engineering
  • Mechanical Engineering

Keywords

  • Computational intelligence
  • Energy index
  • Machine fault prognostics
  • Neuro-fuzzy systems
  • Support vector regression

Fingerprint

Dive into the research topics of 'Prognostics of machine condition using energy based monitoring index and computational intelligence'. Together they form a unique fingerprint.

Cite this