Process knowledge based multi-class support vector classification (PK-MSVM) approach for surface defects in hot rolling

Research highlights? We investigate the random surface defects on hot rolled steel bars and coils. ? Automatic image based inspection technique used for investigation. ? Defects classified based on process knowledge and image processing. ? Process knowledge leads to better classification scheme by support vector machines. Random surface defects occur during the hot bar rolling of steels and are identified either by manual or by automated inspection techniques. Manual inspection techniques are purely based on the process knowledge of the inspector such as the location, type and kind of defects, and the primary sources of these defects. The automated techniques, to identify and classify the defects, rely on machine vision technologies and image processing algorithms based on support vector machines, wavelets, image processing and statistical inference. Both these approaches have their own advantages and limitations. To improve the accuracy of classification of these defects a process knowledge based support vector classification scheme is proposed (called PK-MSVM) which combines feature extraction task of automated inspection with the process knowledge. The defect observation data from the imaging sensor is transformed to include this process knowledge. Three attributes of the defects - length to width ratio, longitudinal location and transverse location- are used for this transformation are they are closely related to the thermo-mechanics of the rolling process. Different formulations of the multi-class support vector machines (MSVMs) are compared for this classification with or without process knowledge based transformation: one-against-one, one-against-all and Hastie's algorithm of multi class SVM. It is found that the new approach (PK-MSVM) performs better than traditional MSVM for all the three formulations. For the best case, the performance sees a jump of more than 100%. Thus incorporating process knowledge in identification and classification does increase the reliability of inspection considerably.

[1]  Gérard Dreyfus,et al.  Single-layer learning revisited: a stepwise procedure for building and training a neural network , 1989, NATO Neurocomputing.

[2]  Yong-Taek Im,et al.  Surface wrinkle defect of carbon steel in the hot bar rolling process , 2009 .

[3]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[4]  J. Brimacombe.  The challenge of quality in continuous casting processes , 1999 .

[5]  Alexander J. Smola,et al.  Learning with kernels , 1998 .

[7]  Jing Li,et al.  On-Line Seam Detection in Rolling Processes Using Snake Projection and Discrete Wavelet Transform , 2007 .

[8]  Rajiv Shivpuri,et al.  Reduction of random seams in hot rolling through FEM based sensitivity analysis , 2006 .

[9]  Kurt Hornik,et al.  kernlab - An S4 Package for Kernel Methods in R , 2004 .

[10]  Sang Woo Kim,et al.  Development of Real-time Defect Detection Algorithm for High-speed Steel Bar in Coil(BIC) , 2006, 2006 SICE-ICASE International Joint Conference.

[11]  Robert Tibshirani,et al.  The Entire Regularization Path for the Support Vector Machine , 2004, J. Mach. Learn. Res..

[12]  Howard Hsun-hau,et al.  Imaging-based In-Line Surface Defect Inspection for Bar Rolling , 2004 .

[13]  Chih-Jen Lin,et al.  A formal analysis of stopping criteria of decomposition methods for support vector machines , 2002, IEEE Trans. Neural Networks.

[14]  Françoise Fogelman-Soulié,et al.  Neurocomputing : algorithms, architectures and applications , 1990 .

[15]  Ulrich H.-G. Kreßel,et al.  Pairwise classification and support vector machines , 1999 .

[16]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

[17]  Jiawei Han,et al.  Data Mining: Concepts and Techniques, Second Edition , 2006, The Morgan Kaufmann series in data management systems.

[18]  Ginzburg.  Steel-Rolling Technology: Theory and Practice , 1989 .

[19]  Chih-Jen Lin,et al.  Probability Estimates for Multi-class Classification by Pairwise Coupling , 2003, J. Mach. Learn. Res..

[20]  Yi Lin.  Multicategory Support Vector Machines, Theory, and Application to the Classification of . . . , 2003 .

[21]  Yi Lu Murphey,et al.  An intelligent real-time vision system for surface defect detection , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[22]  Hsuan-Tien Lin,et al.  A note on Platt’s probabilistic outputs for support vector machines , 2007, Machine Learning.

[23]  John Platt,et al.  Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods , 1999 .

[24]  Kurt Hornik,et al.  Support Vector Machines in R , 2006 .

[25]  SungHoo Choi,et al.  Real-time vision-based defect inspection for high-speed steel products , 2008 .

[26]  Shiyu Zhou,et al.  IDENTIFICATION OF IMPACTING FACTORS OF SURFACE DEFECTS IN HOT ROLLING PROCESSES USING MULTI-LEVEL REGRESSION ANALYSIS , 2004 .

[27]  Alexander J. Smola,et al.  Advances in Large Margin Classifiers , 2000 .