Title: Analysis and interpretation of weld flaws using ANN

Authors: Vijay R. Rathod; R.S. Anand; Alaknanda Ashok

Addresses: Department of Electrical Engineering, Indian Institute of Technology Roorkee, Roorkee 247667, India ' Department of Electrical Engineering, Indian Institute of Technology Roorkee, Roorkee 247667, India ' Scientist 'F' Council of Scientific & Industrial Research, Anusandhan Bhawan, 2 Rafi Ahmed Kidwai Marg, New Delhi 110001, India

Abstract: The paper presents a novel approach for the detection and classification of flaws in weld images is presented. This method has been applied for detecting and discriminating flaws in welds that may correspond to false alarms or possibly all nine types of weld defects (slag inclusion, wormhole, porosity, incomplete penetration, under cuts, cracks, lack of fusion, weaving fault slag line), after being successfully tested on more than 180 radiographic images. The procedure to detect all the types of flaws and feature extraction is implemented by the segmentation algorithm. Classification is carried out by the counter-propagation neural network.

Keywords: radiographic images; weld flaws; image segmentation; region growing; morphological edge detection; multistage watershed transformation; artificial neural networks; ANNs; counter propagation neural networks; weld images; false alarms; weld defects; feature extraction; defect classification.

DOI: 10.1504/IJSISE.2013.054790

International Journal of Signal and Imaging Systems Engineering, 2013 Vol.6 No.3, pp.143 - 149

Received: 19 Apr 2011
Accepted: 06 Aug 2011
Published online: 13 Sep 2013 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article