Detection and classification of weld defects in industrial radiography with use of advanced AI methods

Author

Sikora, Ryszard ; Baniukiewicz, Piotr ; Chady, Tomasz ; Lopato, Przemyslaw ; Piekarczyk, Bogdan ; Psuj, Grzegorz ; Grzywacz, Bogdan ; Misztal, Leszek

Author_Institution

West Pomeranian Univ. of Technol., Szczecin, Poland

fYear

2013

Firstpage

12

Lastpage

17

Abstract

The paper presents and shortly discusses the AI algorithms created for automated detection and classification of weld defects on the basis of radiography images. The three approaches are described: with use of fuzzy logic, with use of artificial neural networks and that basing on rough sets theory. The data evaluating the accuracies of obtained classifiers as well as chosen examples are attached.

Keywords

artificial intelligence; automatic optical inspection; fuzzy logic; image classification; materials science computing; neural nets; radiography; rough set theory; welds; advanced AI method; artificial neural networks; automated detection; fuzzy logic; industrial radiography; rough sets theory; weld defect classification; weld defect detection; Accuracy; Artificial neural networks; Fuzzy logic; Shape; Testing; Training; Welding; automated identification of weld defects; digital radiography; fuzzy logic; neural networks; rough sets;

fLanguage

English

Publisher

ieee

Conference_Titel

Nondestructive Evaluation/Testing: New Technology & Application (FENDT), 2013 Far East Forum on

Conference_Location

Jinan

Print_ISBN

978-1-4673-6018-0

Type

conf

DOI

10.1109/FENDT.2013.6635520

Filename

6635520