AUTOMATED DEFECT CLASSIFICATION USING AN ARTIFICIAL NEURAL NETWORK

Journal Article · Tue Mar 03 00:00:00 EST 2009 · AIP Conference Proceedings

DOI:https://doi.org/10.1063/1.3114147· OSTI ID:21260280

Chady, T; Caryk, M ^[1]; Piekarczyk, B ^[2]

---

1. Szczecin University of Technology, Department of Electrical Engineering (Poland)
2. Technic-Control, Szczecin (Poland)

The automated defect classification algorithm based on artificial neural network with multilayer backpropagation structure was utilized. The selected features of flaws were used as input data. In order to train the neural network it is necessary to prepare learning data which is representative database of defects. Database preparation requires the following steps: image acquisition and pre-processing, image enhancement, defect detection and feature extraction. The real digital radiographs of welded parts of a ship were used for this purpose.

• OSTI ID: 21260280
• Journal Information: AIP Conference Proceedings, Vol. 1096, Issue 1; Conference: 35. annual review of progress in quantitative nondestructive evaluation, Chicago, IL (United States), 20-25 Jul 2008; Other Information: DOI: 10.1063/1.3114147; (c) 2009 American Institute of Physics; Country of input: International Atomic Energy Agency (IAEA); ISSN 0094-243X
• Country of Publication: United States
• Language: English

Related Subjects

71 CLASSICAL AND QUANTUM MECHANICS
GENERAL PHYSICS
ALGORITHMS
CLASSIFICATION
DEFECTS
IMAGE PROCESSING
IMAGES
LAYERS
NEURAL NETWORKS
NONDESTRUCTIVE TESTING