EVALUATION OF MIG WELDING SURFACES USING GAUSSIAN DISTRIBUTION
Keywords:
MIG Welding, Welding Defects, Vision System , Gaussian DistributionAbstract
In this paper, an effort has been taken to assess the qualities of MIG (Metal Inert Gas) welded joints using vision system and the assumption that the vertical section of the surface of a weld image can be estimated by Gaussian distribution(normal curve). The surface variations of the weld image caused by defects are used to categorize welds as good weld, and no weld. This paper consists of two major divisions: weld extraction and surface quality evaluation. Initially weld beads are extracted from the MIG Welded joints through CCD camera of a machine vision system. The grey level values of the pixels from the captured images are assumed to fit a Gaussian distribution, and then determine their qualities. This method is tested with 80 images of good and no weld. Finally, it is concluded that this method may be used for extraction of features in vision inspection system of the quality of welded surfaces.
Downloads
References
Wang G and Liao T W (2002), “Automatic Identification of Different Types of Welding Defects in Radiographic Images”, NDT&E International, Vol. 35, 519-528.
Shafeek H I, Adelmawla E S, Abdel-Shafy A A and Elewa I M (2004), “Automatic Inspection of Gas Pipeline Welding Defects using an Expert Vision System”, NDT&E International, Vol. 37, 301-307.
Jagannathan S (1997), “Automatic Inspection of Wave Soldered Joints using Neural Networks”, Journal of Manufacturing Systems, Vol. 16, 389-398.
Tae-Hyeon Kim, Tai-Hoon Cho, Young Shik Moon, and Sung Han Park (1999), “Visual Inpection System for the Classification of Solder Joints”, Pattern Recognition, Vol. 32, 565-575.
Warren Liao T and Yueming Li (1998), “An Automated Radiographic NDT System Weld Inspection”, NDT&E International, Vol. 31, 183-192.
Warren Liao T (2009), “Improving the Accuracy of Computer-Aided Radiographic Weld Inspection by Feature Selection”, NDT&E International, Vol. 42, 229-239.
Joongho Chang et al (1997), “Cork Quality Classification System using a Unified Image Processing and Fuzzy- Neural Network Methodology”, IEEE Transactions of Networks, Vol. 8, 964-974.
Jagannathan S (1992), “Intelligent Inspection of Wave Soldered Joints - Technical Report”, Journal of Manufacturing Systems, Vol. 11, 137-143.
Romeu R and da Silva et al (2005), “Estimated Accuracy of Classification of Defects Detected in Welded Joints by Radiographic Tests”, NDT&E International, Vol. 38, 335-343.
Gauss M, Buerkle A, Laengle T, Woern H, Stelter J, Ruhmkorf S and Middelmann R (2003), “Adaptive Robot Based Visual Inspection of Complex Parts”, ISR.
Miguel Carrasco and Domingo Merry (2010), “Automatic Multiple View Inspection using Geometrical Tracking and Feature Analysis in Aluminum Wheels”, Machine Vision and Applications.
Veerarajan T (2010), “Probability, Statistics and Random Processes”, Third Edition, Tata McGraw-Hill Publishing.
Gupta S C and Kapoor V K (1999), “Fundamentals of Mathematical Statistics”, Sultan Chand & Sons Publishing.
Sonka M, Hilavac H and Boyle R (1998), “Image Processing, Analysis and Machine Vision”, Second Edition. PWS Publishing (USA).
Sonka M, Hilavac H and Boyle R (2011), “Digital Image Processing and Computer Vision”, Fourth Edition. Cengage Learning Products.
Rafeal C Gonzalez and Richard E Woods (2002), “Digital Image, Second Edition Addison - Wesley.
Sridhar S (2011), “Digital Image Processing”, First Edition, Oxford University Press.
