Abstract

  Thermal imaging is simply the technique of using the heat given off by an object to produce an image of it or locate it. Several thermal imaging frameworks for the detection of defects in welded joints have been introduced in literature. Weld joints are the origin of structural weakness in maximum cases and must be routinely inspected to ensure structural integrity of the fabricated components. Hence the defect detection on welded joints has become a significant task, as it provides the fundamental information for semantic understanding of the scene. This research aims to develop a specialized algorithm that would use the defect’s heat signature for detection, density of defect and applications that takes benefit of this technology. The algorithm is mainly divided into several segments which go like object capturing, Temperature decay variation, filtering, validation etc. It may embed a module for the automatic determination of the range of defect temperature variation using the learn and adapt technology of neurons. This technology surpasses previous approaches like Edge detectors, morphological operators, finding interest points and region of interest, features matching. Certainly, the research outperforms the result obtained by visible images with the boon of most advanced non visible spectrum thermal cameras.

Keywords: Thermal Image; Non - Destructive Evaluation; Infrared Thermography; Adaptive Neural Network

References

1. B Raj., et al. "Non-destructive testing and evaluation for structural integrity”. (1995): 5-38.
2. VHC de Albuquerque., et al. “Evaluation of multilayer perceptron and self-organizing map neural network topologies applied on microstructure segmentation from metallographic images”. NDT and E International 42 (2009): 644-651.
3. "Structural Welding Code -Steel. Miami, United States: American Welding Society”. An American National Standard (2011).
4. TW Liao. "Improving the accuracy of computer-aided radiographic weld inspection by feature selection”. NDT and E International 42 (2009): 229-239.
5. R Sikora., et al. “Automatic Classification of Welding Flaws Using Artificial Intelligence Algorithms”. in AIP Conference Proceedings (2009): 1182-1189.
6. J Zapata., et al. “An adaptive-network-based fuzzy inference system for classification of welding defects”. NDT and E International 43 (2010): 191-199.
7. J Zapata., et al. “Performance evaluation of an automatic inspection system of weld defects in radiographic images based on neuro-classifiers”. Expert Systems with applications 38 (2011): 8812-8824.
8. S Lalithakumari., et al. “Artificial Neural Network based classification of austenitic stainless steel weld defect in TOFD technique”. Indian Journal of Computer Science and Engineering 2 (2012): 845-849.
9. R PV. "Detection of Welding Defects using S-TOFD and Digital Image Processing Techniques”. International Journal of Computer Applications 48 (2012): 23-26.
10. R Sikora., et al. “Artificial neural networks and fuzzy logic in nondestructive evaluation”. Electromagnetic Nondestructive Evaluation 16.38 (2013): 137.
11. T Srikanth and V Kamala. "A Novel Approach for Automatic Detection of Defects in Radiographic Weld Images by Morphological and Statistical Operations”.
12. VR Rathod., et al. “Comparative analysis of NDE techniques with image processing”. Nondestructive Testing and Evaluation 27 (2012): 305-326.
13. TW Liao. "Classification of weld flaws with imbalanced class data”. Expert Systems with applications 35 (2008): 1041-1052.
14. Valavanis and D Kosmopoulos. "Multiclass defect detection and classification in weld radiographic images using geometric and texture features”. Expert Systems with Applications 37 (2010): 7606-7614.
15. JG Wang., et al. “Applying fuzzy method to vision-based lane detection and departure warning system”. Expert Systems with applications 37 (2010): 113-126.
16. GS Kumar., et al. “Vision inspection system for the identification and classification of defects in MIG welding joints”. The International Journal of Advanced Manufacturing Technology 61 (2012): 923-933.
17. E Boldsaikhan., et al. “The use of neural network and discrete Fourier transform for real-time evaluation of friction stir welding”. Applied Soft Computing 11 (2011): 4839-4846.
18. N Yahia., et al. “Automatic detection of welding defects using radiography with a neural approach”. Procedia Engineering 10 (2011): 671-679. 
19. J Shao., et al. “Automatic weld defect detection based on potential defect tracking in real-time radiographic image sequence”. NDT and E International 46 (2012): 14-21. 
20. P Garcia-Allende., et al. “Spectral processing technique based on feature selection and artificial neural networks for arc-welding quality monitoring”. NDT and E International 42 (2009): 56-63. 

Citation

Citation: Akshatha Aravind and Arun VA. “Non Destructive Evaluation of Welded Joints in Hermal Bands Using Neural Networks”. Acta Scientific Computer Sciences 2.1 (2020): 23-27.

Copyright

Copyright: © 2020 Akshatha Aravind and Arun VA. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.