Uncertainty modelling using Dempster-Shafer theory for improving detection of weld defects

Authors:
Valérie Kaftandjian;Olivier Dupuis;Daniel Babot;Yue Min Zhu
Affiliations:
CNDRI, Bat. St. Exupéry, INSA de Lyon, 69621 Villeurbanne, France;CNDRI, Bat. St. Exupéry, INSA de Lyon, 69621 Villeurbanne, France;CNDRI, Bat. St. Exupéry, INSA de Lyon, 69621 Villeurbanne, France;CREATIS, CNRS UMR 5515, Bat. B. Pascal, INSA de Lyon, 69621, Villeurbanne, France
Venue:
Pattern Recognition Letters
Year:
2003

Citing 0
Cited 6

Fault diagnosis of machines based on D-S evidence theory. Part 1: D-S evidence theory and its improvement

Pattern Recognition Letters
Integration study of prospective hazards models for the enhancement of a virtual range simulation model

WSC '05 Proceedings of the 37th conference on Winter simulation
Engine fault diagnosis based on multi-sensor information fusion using Dempster-Shafer evidence theory

Information Fusion
Classification of weld flaws with imbalanced class data

Expert Systems with Applications: An International Journal
Improvement of X-ray castings inspection reliability by using Dempster-Shafer data fusion theory

Pattern Recognition Letters
A fast and robust decision support system for in-line quality assessment of resistance seam welds in the steelmaking industry

Computers in Industry

Quantified Score

Hi-index	0.10

Visualization

Abstract

This paper presents an approach that is based on the combined use of Dempster-Shafer (DS) theory and fuzzy sets for improving automatic detection of weld defects. It consists in modelling detection uncertainty in feature space through using the mass function weighted by membership degrees, and fusing the features of objects using DS com, bination rule. The method is demonstrated on the typical industrial application of weld inspection. The obtained results show that, by modelling detection uncertainty, a confidence level can be associated to each detected object, making the defect detection more precise and reliable.