Automated detection of welding defects in pipelines from radiographic images DWDI

Abstract This paper presents a method for the automatic detection and classification of defects in radiographic images of welded joints obtained by exposure technique of double wall double image (DWDI). The proposed method locates the weld bead on the DWDI radiographic images, segments discontinuities (potential defects) in the detected weld bead and extracts features of these discontinuities. These features are used in a feed-forward multilayer perceptron (MLP) with backpropagation learning algorithm to classify descontinuities in “defect and no-defect”. The classifier reached an accuracy of 88.6% and a F-score of 87.5% for the test data. A comparison of the results with the earlier studies using SWSI and DWSI radiographic images indicates that the proposed method is promising. This work contributes towards the improvement of the automatic detection of welding defects in DWDI radiographic image which results can be used by weld inspectors as a support in the preparation of technical reports.

[1]  W. C. Godoi,et al.  Pattern recognition in the automatic inspection of flaws in polymeric insulators , 2005 .

[2]  Juan Zapata-Pérez,et al.  Performance evaluation of an automatic inspection system of weld defects in radiographic images based on neuro-classifiers , 2011, Expert Syst. Appl..

[3]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[4]  Gang Wang,et al.  Automatic identification of different types of welding defects in radiographic images , 2002 .

[5]  Tania Mezzadri Centeno,et al.  Detecting Central Region in Weld Beads of DWDI Radiographic Images Using PSO , 2015, Int. J. Nat. Comput. Res..

[6]  Rafael C. González,et al.  Digital image processing using MATLAB , 2006 .

[7]  J. López-Higuera,et al.  Real-time arc-welding defect detection and classification with principal component analysis and artificial neural networks , 2007 .

[8]  Ramón Ruiz,et al.  An automatic system of classification of weld defects in radiographic images , 2009 .

[9]  T. Warren Liao,et al.  Improving the accuracy of computer-aided radiographic weld inspection by feature selection , 2009 .

[10]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[11]  Chularat Tanprasert,et al.  Feature windowing-based Thai text-dependent speaker identification using MLP with backpropagation algorithm , 2000, 2000 IEEE International Symposium on Circuits and Systems. Emerging Technologies for the 21st Century. Proceedings (IEEE Cat No.00CH36353).

[12]  B. Rokrok,et al.  Sensitivity Evaluation in Double Wall Radiography of Pipes and Multilayer Plates by Assessment the Monte Carlo Simulation , 2006 .

[13]  Marcio H. S. Siqueira,et al.  Estimated accuracy of classification of defects detected in welded joints by radiographic tests , 2005 .

[14]  George V. Lashkia.  Defect detection in X-ray images using fuzzy reasoning , 2001, Image Vis. Comput..

[15]  T. Warren Liao,et al.  Classification of weld flaws with imbalanced class data , 2008, Expert Syst. Appl..

[16]  Luis Volnei Sudati Sagrilo,et al.  Evaluation of the relevant characteristic parameters of welding defects and probability of correct classification using linear classifiers , 2002 .

[17]  I. M. Elewa,et al.  Automatic inspection of gas pipeline welding defects using an expert vision system , 2004 .

[18]  B. Rokrok,et al.  Scattering and image contrast simulation for double wall radiography of pipes , 2007 .

[19]  Myriam Regattieri Delgado,et al.  Genetic algorithms to automatic weld bead detection in double wall double image digital radiographs , 2012, 2012 IEEE Congress on Evolutionary Computation.

[20]  Guy Lapalme,et al.  A systematic analysis of performance measures for classification tasks , 2009, Inf. Process. Manag..

[21]  Toby P. Breckon,et al.  Fundamentals of Digital Image Processing: A Practical Approach with Examples in Matlab , 2011 .

[22]  Dimitrios Kosmopoulos,et al.  Multiclass defect detection and classification in weld radiographic images using geometric and texture features , 2010, Expert Syst. Appl..

[23]  Martin Fodslette Møller,et al.  A scaled conjugate gradient algorithm for fast supervised learning , 1993, Neural Networks.