A multi-attribute classification fusion for health diagnostics

Prasanna Tamilselvan, Pingfeng Wang

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

Abstract

Efficient health diagnostics provides benefits such as improved safety, improved reliability, and reduced costs for the operation and maintenance of complex engineered systems. This paper presents a multi-attribute classification fusion approach which leverages the strengths provided by multiple membership classifiers to form a robust classification model for structural health diagnostics. This paper developed a novel classification fusion approach for health diagnostics with three primary stages: (i) fusion formulation using a k-fold cross validation model; (ii) diagnostics with multiple multi-attribute classifiers as member algorithms; and (iii) classification fusion through a weighted majority voting with dominance system. State-of-the-art classification techniques from three broad categories (i.e., supervised learning, unsupervised learning, and statistical inference) were employed as the member algorithms. The proposed classification fusion approach is demonstrated with bearing health diagnostics problem. In the bearing case study, the proposed approach outperforms any stand-alone member algorithm with better diagnostic accuracy and robustness.

Original languageEnglish (US)
Title of host publication54th AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference
StatePublished - Aug 15 2013
Externally publishedYes
Event54th AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference - Boston, MA, United States
Duration: Apr 8 2013Apr 11 2013

Publication series

NameCollection of Technical Papers - AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference
ISSN (Print)0273-4508

Other

Other54th AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference
Country/TerritoryUnited States
CityBoston, MA
Period4/8/134/11/13

ASJC Scopus subject areas

  • Architecture
  • Materials Science(all)
  • Aerospace Engineering
  • Mechanics of Materials
  • Mechanical Engineering

Fingerprint

Dive into the research topics of 'A multi-attribute classification fusion for health diagnostics'. Together they form a unique fingerprint.

Cite this