AN INDUSTRIAL INSPECTION APPROACH FOR WELD DEFECTS USING MACHINE LEARNING ALGORITHM
DOI:
https://doi.org/10.29284/ijasis.5.1.2019.15-21Keywords:
X-ray weld images, weld image classification, speeded-up robust features, machine learning, auto-encoder classifierAbstract
The weld defects are formed due to the incorrect welding patterns or wrong welding process. The defects in the weld may vary from size, shape and their projected quality. The most common weld defects occur during welding process is slag inclusions, porosity, lack of fusion and incomplete penetration. In this study, an effective method for weld defect classification using machine learning algorithm is presented. The system uses Speeded-up Robust Features (SURF) for feature extraction and one of the machine learning algorithms called Auto-Encoder Classifier (AEC) for classification. Initially, the features that distinguish weld defects and no defects in the weld image are extracted by SURF. Then, AEC is analyzed for weld image classification using different number of neurons in different hidden layers (2 and 3 hidden layers). The performance of the system is evaluated by GD X-ray weld image database. The results show that the weld images are correctly classified with 98% accuracy using SURF and AEC.
Downloads
References
A. Khumaidi, E.M. Yuniarno, and M.H. Purnomo, “Welding defect classification based on convolution neural network (CNN) and Gaussian kernel”, International Seminar on Intelligent Technology and Its Applications, 2017, pp. 261-265.
G. Fei, and W. Kehong, “The research of classification method of arc welding pool image based on invariant moments”, IEEE Power Engineering and Automation Conference, Vol. 3, 2011, pp. 73-76.
A.A. Moghaddam, “Image processing techniques for classification of linear welding defects”, International Conference on Knowledge-Based Engineering and Innovation, 2015, pp. 978-981.
M. Sundaram, J.P. Jose, and G. Jaffino, “Welding defects extraction for radiographic images using C-means segmentation method”, International Conference on Communication and Network Technologies, 2014, pp. 79-83.
F. Mekhalfa, and N. Nacereddine, “Multiclass classification of weld defects in radiographic images based on support vector machines”, International Conference on Signal-Image Technology and Internet-Based Systems, 2014, pp. 1-6.
F. Mekhalfa, and N. Nacereddine, “Gentle Adaboost algorithm for weld defect classification”, Signal Processing: Algorithms, Architectures, Arrangements, and Applications, 2017, pp. 301-306.
J. Hassan, A.M. Awan, and A. Jalil, “Welding defect detection and classification using geometric features”, International Conference on Frontiers of Information Technology, 2012, pp. 139-144.
J. Kumar, R.S. Anand, and S.P. Srivastava, “Flaws classification using ANN for radiographic weld images”, International Conference on Signal Processing and Integrated Networks, 2014, pp. 145-150.
A. Muniategui, B. Hériz, L. Eciolaza, M. Ayuso, A. Iturrioz, I. Quintana, and P. Álvarez, “Spot welding monitoring system based on fuzzy classification and deep learning”, International Conference on Fuzzy Systems, 2017, pp. 1-6.
D. Gao, Y.X. Liu, and X.G. Zhang, “Binary-tree multi-classifier for welding defects and its application based on SVM”, World Congress on Intelligent Control and Automation, Vol. 2, 2006, pp. 8509-8513.
Y. Hanbing, Z. Lina, and J. Hui, “Research on SVM Based Classification for Welding Defects in Radiographic Testing”, International Congress on Image and Signal Processing, 2009.
X. Tian, C. Wang, and H. Zhang, “Extraction of object features from high resolution SAR images based on SURF features”, IEEE International Geoscience and Remote Sensing Symposium, 2011, pp. 1802-1805.
Y. Sakai, T. Oda, M. Ikeda, and L. Barolli, “An object tracking system based on sift and surf feature extraction methods”, International Conference on Network-Based Information Systems, 2015, pp. 561-565.
Y. Sun, J. Li, W. Wang, A. Plaza, and Z. Chen, “Active learning based autoencoder for hyperspectral imagery classification”, International Geoscience and Remote Sensing Symposium, 2016, pp. 469-472.
H. Badem, A. Caliskan, A. Basturk, and M.E. Yuksel, “Classification of human activity by using a Stacked Autoencoder”, Medical Technologies National Congress, 2016, pp. 1-4.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
