Jam Detector for Steel Pickling Lines Using Machine Vision

High efficiency and availability in industrial processing lines are requirements to produce top-grade steel at a minimum cost. One of the most important aspects in achieving these goals is efficient automation, which ensures high performance and reduces the cost of production. This work proposes a new system to improve the automation of a steel processing line: a jam detector based on machine vision. The proposed system is designed to detect jams in a crucial step in steel production: pickling. The proposed machine-vision application acquires images from the pickling line and detects the jam based on the number of pieces ejected from the side trimmers. State-of-the-art methods are used for image processing, providing a fast and robust detector for the industrial line. Tests and the results obtained after more than one year of operation in a steel processing plant indicate that the proposed system meets production needs.

[1]  Jitendra Malik,et al.  A real-time computer vision system for measuring traffic parameters , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[2]  Zhengyi Jiang,et al.  High temperature oxide scale characteristics of low carbon steel in hot rolling , 2004 .

[3]  Daniel F. García,et al.  A flexible software architecture for scalable real-time image and video processing applications , 2012, Real-Time Image and Video Processing.

[4]  I. Olefjord,et al.  Surface reactions during pickling of an aluminium-magnesium-silicon alloy in phosphoric acid , 2001 .

[5]  D.F. Garcia,et al.  Real-Time Assessment of the Reliability of Welds in Steel Strips , 2010, IEEE Transactions on Industry Applications.

[6]  Bülent Sankur,et al.  Survey over image thresholding techniques and quantitative performance evaluation , 2004, J. Electronic Imaging.

[7]  Josef Kittler,et al.  A survey of the hough transform , 1988, Comput. Vis. Graph. Image Process..

[8]  Massimo Piccardi,et al.  Background subtraction techniques: a review , 2004, 2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583).

[9]  Alex Pentland,et al.  Pfinder: Real-Time Tracking of the Human Body , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Kunio Sekiguchi,et al.  Advanced set-up and control system for Dofasco's tandem cold mill , 1994, Proceedings of 1994 IEEE Industry Applications Society Annual Meeting.

[11]  Bidyut Baran Chaudhuri,et al.  A survey of Hough Transform , 2015, Pattern Recognit..

[12]  R. I. Stephens,et al.  On-line adaptive control in the hot rolling of steel , 1997 .

[13]  W. Eric L. Grimson,et al.  Adaptive background mixture models for real-time tracking , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[14]  Euripides G. M. Petrakis,et al.  A survey on industrial vision systems, applications, tools , 2003, Image Vis. Comput..

[15]  Alex Pentland,et al.  Pfinder: real-time tracking of the human body , 1996, Proceedings of the Second International Conference on Automatic Face and Gesture Recognition.

[16]  Christian Mirth.  Low-Level Features from Video for Traffic Jam Detection , 2008 .

[17]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Bohyung Han,et al.  SEQUENTIAL KERNEL DENSITY APPROXIMATION THROUGH MODE PROPAGATION: APPLICATIONS TO BACKGROUND MODELING , 2004 .