Online Multichannel Forging Tonnage Monitoring and Fault Pattern Discrimination Using Principal Curve

[+] Author and Article Information
Jihyun Kim

Research Institute for Information and Communication Technology, Korea University, Seoul, Korea

Qiang Huang1

Department of Industrial and Management Systems Engineering, The University of South Florida, Tampa, FL 33620huangq@eng.usf.edu

Jianjun Shi

Department of Industrial and Operations Engineering, The University of Michigan, Ann Arbor, MI 48109

Tzyy-Shuh Chang

 OG Technologies, Inc., 58 Parkland Plaza Suite 200, Ann Arbor, MI 48103


Author to whom correspondence should be addressed.

J. Manuf. Sci. Eng 128(4), 944-950 (Sep 02, 2005) (7 pages) doi:10.1115/1.2193552 History: Received December 02, 2003; Revised September 02, 2005

Due to the late response to process condition changes, forging processes are normally exposed to a large number of defective products. To achieve online process monitoring, multichannel tonnage signals are often collected from the forging press. The tonnage signals contain significant amount of real time information regarding the product and the process conditions. In this paper, a methodology is developed to detect profile changes of multichannel tonnage signals for forging process monitoring and to classify fault patterns. The changes include global or local profile deviations, which correspond to deviations of a whole process cycle or process segment(s) within a cycle, respectively. The principal curve method is used to conduct feature extraction and discrimination of tonnage signals. The developed methodology is demonstrated with industry data from a crankshaft forging processes.

Copyright © 2006 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.



Grahic Jump Location
Figure 2

Forging press and tonnage sensor locations

Grahic Jump Location
Figure 3

Tonnage signals from four tonnage sensors

Grahic Jump Location
Figure 4

Flow chart of the proposed methodology

Grahic Jump Location
Figure 5

Segmentation of the tonnage signal and the segment intervals

Grahic Jump Location
Figure 6

Tonnage signal monitoring based on peak values

Grahic Jump Location
Figure 7

CDF plots of overall squared distances

Grahic Jump Location
Figure 8

Discrimination limits for case 1

Grahic Jump Location
Figure 9

Discrimination limits for segment 2 to segment 6 (a) segment 2; (b) Segment 3; (c) Segment 4; (d) Segment 5; (e) Segment 6



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.

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