AUTOMATIC INSPECTION FOR MIG WELDING JOINTS USING MACHINE VISION
Keywords:
Machine Vision, Weld Classification, MIG Welding, Vision Inspection Back Propagation Neuralnetwork (BPN)Abstract
In this study, we use machine vision to inspection of welding surfaces produced by the MIG welding Process. Machine vision allows for the inspection of welded surfaces without touching or scratching the surface, and provides the flexibility for inspection parts. In this experimental work, inspection system has been developed for identifying and classifying the surface defects of fillet joint as per standard EN25817 in Metal Inert Gas (MIG) welding. In this proposed vision system, images of welding surfaces are captured through CCD camera. From these images, the regions of interest are segmented and the average gray levels of the characteristic features of these images are calculated.. Finally, welded joints can be classified into one of the four pre-defined ones based on the back propagation neural network. This proposed system, 80 welded samples are analysed with two different feature extraction methods.
Downloads
References
Tae-Hyeon Kim, Tai-Hoon Cho, Young Shik Moon and Sung Han Park (1999), “Visual Inspection System for the Classification of Solder Joints”, Pattern Recognition, Vol. 32, 565-575.
S. Jagannathan (1997), “Automatic Inspection of Wave Soldered Joints using Neural Networks”, Journal of Manufacturing Systems, Vol. 16.
Jagannathan S (1990), “Intelligent Inspection of Wave Soldered Joints - Technical Report”, Journal of Manufacturing Systems, Vol. 11.
Elias N, Malamas, Euripides G M, Petrakis, Michalis Zervakis, Laurent Petit (2003), “A Survey on Industrial Vision Systems, Applications and Tools Image and computing”, Vol. 21, 171-188.
Liao T W, Li D M and Li Y M (1999), “Detection of Welding Flaws from Radiographic Images with Fuzzy Clustering Methods”, Fuzzy Sets and Systems, Vol. 108, 145-158.
Waren Liao T and Tang K (1997), “Automated Extraction of Welds from Digitized Radiographic Images based on MLP Neural Networks”, Applied Artificial Intelligence, Vol. 11, 197-218.
Waren Liao T, Damin Li and Yueming Li (2000), “Extraction of Welds from Radiographic Images using Fuzzy Classifiers”, Information Sciences, Vol. 126, 21-40.
Lashkia V (2001), “Defect Detection in X-ray Images using fuzzy reasoning”, Image and Vision Computing, Vol. 19, 261-269.
Gauss M, Buerkle A, Laengle T, Woern H, Stelter J, Ruhmkorf S and Middelmann R (2003), “Adaptive Robot based Visual Inspection of Complex Parts”, ISR2003.
Liao T W (2003), “Classification of Welding Flaw types with Fuzzy Expert Systems”, Expert Systems with Application, Vol. 25, 101-111.
Romeu R, Da Silva, Luiz P, Caloba, Marcio H S, Siqueira, Joao M A and Rebello (2004), “Pattern Recognition of Weld Defects Detected by Radiographic Test”, NDT&E International Vol. 37, 461-470.
Rafael Vilar, Juan Zapata and Ramon Ruiz (2009), “An Automatic System of Classification of Weld Defects in Radiographic Images”, NDT&E International, Vol. 42, 467-476.
Yan Wang, Yi Sun, Peng L V and Hao Wang (2008), “Detection of Line Weld Defects based on Multiple Thresholds and Support Vector Machine”, NDT&E International, Vol. 41, 517-524.
Garcia-Allende P B, Mirapeix J, Conde O M, Cobo A and Lopez-Higuera J M (2009), “Spectral Processing Technique based on Feature Selection and Artificial Neural Networks for Arc-Welding Quality Monitoring”, NDT&E International, Vol. 42, 56-63.
Miguel Carrasco and Domingo Merry (2010), “Automatic Multiple View Inspection using Geometrical Tracking and Feature Analysis in Aluminum Wheels”, Machine Vision and Applications.
Liao T W and Li Y M (2000), “An Automated Radiographic NDT System for Weld Inspection: part II- Flaw Detection”, NDT &E International, Vol. 31, 183-192.
Senthilkumar G, Natarajan U and Ananthan S S (2011), “Vision Inspection System for the Identification and Classification of Defects in MIG Welding Joints”, The International Journal of Advanced Manufacturing Technology.
Senthilkumar G, Natarajan U and Sankaranarayanan G (2011), “Performace Evaluation of Vision Inspection System for MIG Welding Defects”, DOI:AA042011002.
