0
Research Papers

Automatic Tonnage Monitoring for Missing Part Detection in Multi-Operation Forging Processes

[+] Author and Article Information
Yong Lei

State Key Laboratory of Fluid Power Transmission and Control, Zhejiang University, Hangzhou 310027, Chinaylei@zju.edu.cn

Zhisheng Zhang

College of Mechanical Engineering, Southeast University, Nanjing 210096, Chinaoldbc@seu.edu.cn

Jionghua Jin1

Department of Industrial and Operations Engineering, University of Michigan, Ann Arbor, MI 48105jhjin@umich.edu

1

Corresponding author.

J. Manuf. Sci. Eng 132(5), 051010 (Oct 04, 2010) (10 pages) doi:10.1115/1.4002531 History: Received November 05, 2008; Revised August 11, 2010; Published October 04, 2010; Online October 04, 2010

In multi-operation forging processes, the process fault due to missing parts from dies is a critical concern. The objective of this paper is to develop an effective method for detecting missing parts by using automatic classification of tonnage signals during continuous production. In this paper, a new feature selection and hierarchical classification method is developed to improve the classification performance for multiclass faults. In the development of the methodology, the signal segmentation is conducted at the first step based on an offline station-by-station test in a forging process. Afterwards, the principal component analysis is conducted on the segmented tonnage signals to generate the principal component (PC) features to be selected for designing the classifier. Finally, the optimal selection of PC features is integrated with the design of a hierarchical classifier by using the criterion of minimizing the probabilities of misclassification among classes. A case study using a real-world forging process is provided in the paper, which demonstrates the effectiveness of the developed methodology for detecting and diagnosing the missing parts faults in the multiple forging operation process. The classifier performance is also validated through the cross-validations to achieve a given average classification error.

FIGURES IN THIS ARTICLE
<>
Copyright © 2010 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Figure 1

Sensor distributions in the forging machine

Grahic Jump Location
Figure 2

Tonnage signal comparison due to missing weak operation forces

Grahic Jump Location
Figure 3

Sketched billet and workpiece passing through five operations in a forging process

Grahic Jump Location
Figure 4

Sample tonnage signals at six different conditions

Grahic Jump Location
Figure 5

Training procedures for classifier design

Grahic Jump Location
Figure 6

The decomposed individual signals at each working station

Grahic Jump Location
Figure 7

Hierarchical structure of inclined binary-tree classifier

Grahic Jump Location
Figure 8

Flowchart for optimal feature subset selection and classifier design

Grahic Jump Location
Figure 9

Sample spaces at hierarchical step j

Grahic Jump Location
Figure 10

Three selected segments and PCA analysis results

Grahic Jump Location
Figure 11

Classification results step by steps (a)–(e)

Tables

Errata

Discussions

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