Abnormal State Diagnosis of Sintering Image Based on SVM

Abnormal sintering state is often caused by the changes of improper operation in the sintering process of rotary kiln. If not addressed immediately, control system performance will be deteriorating, and even the crash will be caused. Current approaches of pattern recognition cannot be applied immediately to recognizing such abnormal sintering state of rotary kiln. Therefore, integrating both image processing method and support vector machines(SVM), this paper studies a new and enhanced approach on state recognition of abnormal sintering image, namely,image pretreatment, image segmentation, features extraction, automatic choice of SVM parameters and abnormal state diagnosis technology of sintering image in rotary kiln. Finally, the experimental results show the effectiveness of the approach.

[1]  Federico Girosi,et al.  Training support vector machines: an application to face detection , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[2]  Sayan Mukherjee,et al.  Choosing Multiple Parameters for Support Vector Machines , 2002, Machine Learning.

[3]  Nello Cristianini,et al.  The Learning Methodology , 2000 .

[4]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[5]  Xie Yuan-dan,et al.  Survey on Image Segmentation , 2002 .

[6]  Guido Smits,et al.  Improved SVM regression using mixtures of kernels , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[7]  Zhi Zhan-jiang.  Survey on the Image Segmentation , 2006 .

[8]  Yunqian Ma,et al.  Practical selection of SVM parameters and noise estimation for SVM regression , 2004, Neural Networks.

[9]  Zhao Zhong.  Scale Co-occurrence Matrix for Texture Analysis Using Wavelet Transform , 2001 .

[10]  Michael Krystek,et al.  A fast gauss filtering algorithm for roughness measurements , 1996 .

[11]  Li Shu.  NEURAL NETWORK CONTROL SYSTEM FOR ROTARY KILN BASED ON FEATURES OF COMBUSTION FLAME , 2002 .

[12]  Simon Haykin,et al.  Support vector machines for dynamic reconstruction of a chaotic system , 1999 .

[13]  E. T. Copson.  Asymptotic Expansions: The method of steepest descents , 1965 .

[14]  Zhang Xuegong,et al.  INTRODUCTION TO STATISTICAL LEARNING THEORY AND SUPPORT VECTOR MACHINES , 2000 .

[15]  G. Arfken.  Mathematical Methods for Physicists , 1967 .