A comparative study of evidence theories in the modeling, analysis, and design of engineering systems

S. S. Rao, K. K. Annamdas

Research output: Contribution to journalArticle

12 Scopus citations

Abstract

The application of different types of evidence theories in the modeling, analysis and design of engineering systems is explored. In most studies dealing with evidence theory, the Dempster-Shafer theory (DST) has been used as the framework not only for the characterization and representation of uncertainty but also for combining evidence. The versatility of the theory is the motivation for selecting DST to represent and combine different types of evidence obtained from multiple sources. In this work, five evidence combination rules, namely, Dempster-Shafer, Yager, Inagaki, Zhang, and Murrphy combination rules, are considered. The limitations and sensitivity of the DST rule in the case of conflicting evidence are illustrated with examples. The application of all the five evidence combination rules for the modeling, analysis and design of engineering systems is illustrated using a power plant failure example and a welded beam problem. The aim is to understand the basic characteristics of each rule and develop preliminary guidelines or criteria for selecting an evidence combination rule that is most appropriate based on the nature and characteristics of the available evidence. Since this work is the first one aimed at developing the guidelines or criteria for selecting the most suitable evidence combination rule, further studies are required to refine the guidelines and criteria developed in this work.

Original languageEnglish (US)
Article number061006
JournalJournal of Mechanical Design, Transactions of the ASME
Volume135
Issue number6
DOIs
StatePublished - Jul 15 2013

ASJC Scopus subject areas

  • Mechanics of Materials
  • Mechanical Engineering
  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design

Fingerprint Dive into the research topics of 'A comparative study of evidence theories in the modeling, analysis, and design of engineering systems'. Together they form a unique fingerprint.

  • Cite this