Research Papers

On-Line Bleeds Detection in Continuous Casting Processes Using Engineering-Driven Rule-Based Algorithm

[+] Author and Article Information
Ershun Pan, Liang Ye

Department of Industrial Engineering and Logistics Engineering, Shanghai Jiao-tong University, Shanghai 200030, P. R. China

Jianjun Shi1

School of Industrial and System Engineering, Georgia Institute of Technology, Atlanta, GA 30332-0205jianjun.shi@isye.gatech.edu

Tzyy-Shuh Chang

 OG Technologies, Inc., 4300 Varsity Drive, Suite C, Ann Arbor, MI 48108


Corresponding author.

J. Manuf. Sci. Eng 131(6), 061008 (Dec 02, 2009) (9 pages) doi:10.1115/1.4000560 History: Received November 24, 2008; Revised October 24, 2009; Published December 02, 2009; Online December 02, 2009

This paper describes the development of an on-line quality inspection algorithm for detecting the surface defect (“bleeds”) generated in continuous casting processes. The challenges of bleed detection in visual images lie in the low signal-to-noise ratio, the irregularity of bleed contour patterns, and significant false positives. In order to solve these problems, an engineering-driven rule-based detection (ERD) method is proposed. The ERD consists of three detection stages using the pixel features of bleeds, which are transferred from the physical features generated via engineering knowledge. The detailed strategy, ERD algorithm, parameter selection, and casting knowledge are presented. The real case study demonstrates that the developed algorithm is effective and applicable.

Copyright © 2009 by American Society of Mechanical Engineers
Topics: Casting , Algorithms
Your Session has timed out. Please sign back in to continue.



Grahic Jump Location
Figure 1

Schematic representation of a continuous casting process with the vision sensing system and its surface image

Grahic Jump Location
Figure 2

Subimages of real bleeds

Grahic Jump Location
Figure 3

Subimages of false positive samples

Grahic Jump Location
Figure 4

Framework of the proposed ERD strategy

Grahic Jump Location
Figure 5

The physical mechanism of bleed formation due to rise and fall of metal level and sticking of the newly solidifying shell to the mold wall (revised from Fig. 26 of Ref. 1)

Grahic Jump Location
Figure 6

Illustration of geometric size of bleed contours

Grahic Jump Location
Figure 7

The proposed rule-based features for crescent-shaped contours

Grahic Jump Location
Figure 8

Normality test of bleed width’s distribution

Grahic Jump Location
Figure 9

Bleed detection errors under different settings of gamma

Grahic Jump Location
Figure 10

Detection process of the proposed ERD algorithm




Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In