Real-Time Testing of Steel Strip Welds based on Bayesian Decision Theory

Authors: Julio Molleda, Daniel F. García, Juan C. Granda, Francisco J. Suárez

Abstract:

One of the main trouble in a steel strip manufacturing line is the breakage of whatever weld carried out between steel coils, that are used to produce the continuous strip to be processed. A weld breakage results in a several hours stop of the manufacturing line. In this process the damages caused by the breakage must be repaired. After the reparation and in order to go on with the production it will be necessary a restarting process of the line. For minimizing this problem, a human operator must inspect visually and manually each weld in order to avoid its breakage during the manufacturing process. The work presented in this paper is based on the Bayesian decision theory and it presents an approach to detect, on real-time, steel strip defective welds. This approach is based on quantifying the tradeoffs between various classification decisions using probability and the costs that accompany such decisions.

Keywords: Classification, Pattern Recognition, ProbabilisticReasoning, Statistical Data Analysis.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1081319

References:

[1] G. E. Cook, R. J. Barnett, K. Andersen, J. F. Springfield, A. M. Strauss, "Automated Visual Inspection and Interpretation System for Weld Quality Evaluation". Industry Applications Conference, IEEE 1995.
[2] Lars Hildebrand, Madjid Fathi, "Vision Systems for the Inspection of Resistance Welding Joints". Human Vision and Electronic Imaging, Proc. SPIE Vol. 3959, Jun 2000.
[3] Xiao-Guang Zhang, Jian-Jian Xu, Guang-Ying Ge, "Defects Recognition on X-Ray Images for Weld Inspection using SVM". Machine Learning and Cybernetics, IEEE 2004.
[4] Yi Sun, En-Liang Wang, Peng Zhou, Mohan Li, "Real-Time Weld Defect Inspection System in X-Ray Images". Optical Information Processing Technology, Proc. SPIE Vol. 4929, Sep 2002.
[5] Wolfram A. Karl Deutsch, "Automated Ultrasonic Inspection". October, 2000.
[6] Stephen W. Kercel, Roger A. Kisner, Marvin B. Klein, Gerald D. Bacher, Bruno F. Pouet, "In-Process Detection of Welds Defects Using Laser-Based Ultrasound". Environment Sensors II, Proc. SPIE Vol. 3852, Dec 1999.
[7] S. Adolfson, A. Bahrami, I. Claesson, "Quality Monitoring in Robotised Welding using Sequential Probability Ratio Test". Digital Signal Processing Applications, IEEE 1996.
[8] A. Er├ºil, "Classification Tress Prove Useful in Nondestructive Testing of Spot Weld Quality". Welding Journal. September 1993, pp. 59−67.
[9] A. Erçil, "Regression Trees for Weld Quality Inspection". Bogaziçi University Research Report FBE - EM 92/14, 1992.
[10] J. M. Quero, R. L. Millan, L. G. Franquelo, "Neural Network Approach to Weld Quality Monitoring". Industrial Electronics, Control and Instrumentation, IEEE 1994.
[11] N. Ivezic, J. D. Alien, T. Zacharia, "Neural Network-Based Resistance Spot Welding Control and Quality Prediction". Intelligent Processing and Manufacturing of Materials, IEEE 1999.
[12] J. Molleda, D.F. Garc├¡a, D. Gonz├ílez, I. Peteira, J. A. Gonz├ílez, "Fuzzy−Based Approach to Real−Time Detection of Steel Strips Detective Welds". Computational Intelligence for Measurement Systems and Applications, IEEE 2005.
[13] SangRyong Lee, YoonJun Choo, TaeYoung Lee, ChangWoo Han, MyunHee Kim, "Neuro−Fuzzy Algorithm for Quality Assurance of Resistance Spot Welding". Industry Applications Conference, IEEE 2000.
[14] Chun-Hua Zhang, Li Di, Zeng An, "Welding Quality Monitoring and Management System Based on Data Mining Technology". Machine Learning and Cybernetics, IEEE 2003.
[15] Richard O. Duda, Peter E. Hart, David G. Stork, "Pattern Classification", 2nd Edition, 2001. Wiley. ISBN: 0−471−05669−3.
[16] John W. Sheppard, Mark A. Kaufman, "A Bayesian Approach to Diagnosis and Prognosis Using Built-In Test". Transactions on Instrumentation and Measurement, IEEE 2005.