0
Research Papers

Automated Surface Defect Detection Using High-Density Data

[+] Author and Article Information
Lee J. Wells

Department of Industrial and Entrepreneurial
Engineering & Engineering Management,
Western Michigan University,
Kalamazoo, MI 49008
e-mail: lee.wells@wmich.edu

Mohammed S. Shafae

Grado Department of Industrial and Systems
Engineering,
Virginia Tech,
Blacksburg, VA 24061;
Production Engineering Department,
Faculty of Engineering,
Alexandria University,
Alexandria 21544, Egypt
e-mail: shafae1@vt.edu

Jaime A. Camelio

Grado Department of Industrial and Systems
Engineering,
Virginia Tech,
Blacksburg, VA 24061
e-mail: jcamelio@vt.edu

Manuscript received December 22, 2014; final manuscript received December 16, 2015; published online March 8, 2016. Assoc. Editor: Robert Gao.

J. Manuf. Sci. Eng 138(7), 071001 (Mar 08, 2016) (10 pages) Paper No: MANU-14-1700; doi: 10.1115/1.4032391 History: Received December 22, 2014; Revised December 16, 2015

State-of-the-art measurement technologies, such as 3D laser scanners, provide new opportunities for knowledge discovery and development of quality control (QC) strategies for complex manufacturing systems. These technologies can rapidly provide millions of data points to represent a manufactured part's surface. The resulting high-density (HD) datasets have a great potential to be used for inspecting parts for surface and feature abnormalities. The current use of these datasets for part inspection can be divided into two main categories: (1) extracting feature parameters, which does not complement the nature of these datasets as it wastes valuable data and (2) an ad hoc inspection process, where a visual representation of the data is manually analyzed, which tends to suffer from slow, inefficient, and inconsistent inspection results. To overcome these deficiencies, this paper proposes an adaptive generalized likelihood ratio (AGLR) technique to automate the surface defect inspection process using HD data. This paper presents the performance results of the proposed AGLR approach with respect to the probability of detecting varying size and magnitude defects in addition to the probability of false alarms. In addition, a formal approach for designing an optimal AGLR inspection system is proposed. Finally, simulation results are presented and analyzed to showcase the performance gains of the AGLR approach versus a more traditional generalized likelihood ratio (GLR) approach.

FIGURES IN THIS ARTICLE
<>
Copyright © 2016 by ASME
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Fig. 1

(a) A planar point cloud containing a surface flaw located in the bottom left corner and (b) a zoomed in view of the surface flaw

Grahic Jump Location
Fig. 2

A planar point cloud where 1% of the data falls outside tolerance limits due to (a) noisy data and (b) existence of a fault

Grahic Jump Location
Fig. 3

A planar point cloud with a fault in the center (a) before and (b) after implementing a filter

Grahic Jump Location
Fig. 4

ROI seed structure

Grahic Jump Location
Fig. 5

Allocation of initial ROI. Growth process begins at node A, as illustrated in the Appendix.

Grahic Jump Location
Fig. 6

Simulated false alarm probabilities for varying ROI seed sizes and go/no-go thresholds for AGLR method (black lines) and GLR method (gray lines)

Grahic Jump Location
Fig. 7

Simulated ROC curves for fault (a) F1, (b) F2, (c) F3, (d) F4, (e) F5, (f) F6, (g) F7, (h) F8, and (i) F9 for AGLR method (black lines) and GLR method (gray lines). It must be noted that these figure use the same legend as Fig. 6.

Grahic Jump Location
Fig. 8

Simulated detection probabilities for fault (a) F1, (b) F2, (c) F3, (d) F4, (e) F5, (f) F6, (g) F7, (h) F8, and (i) F9 for AGLR method. It must be noted that these figures use the same legend as Fig. 6.

Grahic Jump Location
Fig. 9

Expected inspection system costs for AGLR method (black lines) and GLR method (gray lines). It must be noted that these figures use the same legend as Fig. 6.

Grahic Jump Location
Fig. 10

ROI growth strategy

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