Using ensembles of binary case-based reasoners

  • Authors:
  • Bill Cheetham;Joe Shultz

  • Affiliations:
  • General Electric Global Research, Niskayuna, NY;General Electric Global Research, Niskayuna, NY

  • Venue:
  • ICCBR'05 Proceedings of the 6th international conference on Case-Based Reasoning Research and Development
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

An ensemble of case-based reasoning systems was created to diagnose unplanned shutdowns of large gas turbines. One case-based reasoning system was created for each of the four most common causes of the shutdowns. Each of these reasoners determines its confidence that the root cause it diagnoses is the actual root cause or not. A fusion module combines these confidence values into a single diagnosis for the shutdown.