Research Papers

Machine Recognition of Laser Reflection From Gas Metal Arc Weld Pool Surfaces

[+] Author and Article Information
ZhenZhou Wang, XiaoJi Ma

Institute for Sustainable Manufacturing and Department of Electrical and Computer Engineering,  University of Kentucky, Lexington, KY 40506

YuMing Zhang1

Institute for Sustainable Manufacturing and Department of Electrical and Computer Engineering,  University of Kentucky, Lexington, KY 40506ymzhang@engr.uky.edu


Corresponding author.

J. Manuf. Sci. Eng 133(4), 041013 (Aug 11, 2011) (13 pages) doi:10.1115/1.4004498 History: Received September 29, 2010; Revised June 16, 2011; Published August 11, 2011; Online August 11, 2011

The reflection of projected laser lines may be used to determine the three-dimensional geometry of the reflecting weld pool surface. However, for gas metal arc welding (GMAW), the transfer of the droplets into the weld pool makes the weld pool surface highly dynamic and fluctuating. The position and geometry of the local reflecting surface, which intercepts and reflects the projected laser changes rapidly. As a result, the reflection rays change their trajectories rapidly. The contrast of laser reflection with the background is much reduced and methods are needed to extract laser reflection from low contrast images. To this end, an image quality measurement method is proposed based on the number of the edge points to determine if an image may be further processed. The image to be processed is then modeled as a superposition of the laser reflection and arc radiation background. Methods have been proposed to remove the uneven distribution of the arc radiation background from the image, such that a global threshold is possible to segment the laser reflection lines. The set of the laser line points are then clustered to form separate laser lines. These laser lines are then modeled and the parameters in the models are used to validate each modeled line. Processing results verified the effectiveness of the proposed methods/algorithms in providing laser lines from low contrast images that are formed by laser reflection from a high dynamic gas metal arc weld pool surface.

Copyright © 2011 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.



Grahic Jump Location
Figure 1

Image of weld pool surface acquired through synchronization of ultrahigh speed shutter and ultrashort laser pulse and use of frosted glass [5-6]

Grahic Jump Location
Figure 2

Experimental system

Grahic Jump Location
Figure 3

Example image and its enhancement

Grahic Jump Location
Figure 4

Current waveform for a GMAW experiment

Grahic Jump Location
Figure 5

Frame 1 in a cycle

Grahic Jump Location
Figure 6

Frame 339 in a cycle. Edge summation 5551.

Grahic Jump Location
Figure 7

Frame 340 in a cycle. Edge summation 5703.

Grahic Jump Location
Figure 8

Frame 341 in a cycle. Edge summation 5655.

Grahic Jump Location
Figure 9

Frame 342 in a cycle. Edge summation 5617.

Grahic Jump Location
Figure 10

Frame 343 in a cycle. Edge summation 5661.

Grahic Jump Location
Figure 11

Frame 344 in a cycle. Edge summation 5653.

Grahic Jump Location
Figure 12

Sums of edges in two sequences of frames (a) sum of edges in frames 1–30 and (b) sum of edges in frames 321–350

Grahic Jump Location
Figure 13

Plot of the 100th and 300th columns of a raw image (a) enhanced Image, (b) T = 10, (c) T = 9, (d) T = 8, (e) T = 7, and (f ) T = 6

Grahic Jump Location
Figure 14

Global thresh-holding results (a) column 100 and (b) column 300

Grahic Jump Location
Figure 15

Grayscale distributions of column 100th and column 300th in enhanced image Fig. 3

Grahic Jump Location
Figure 16

Image column difference and analysis (a) image after column difference with d = 10 and (b) resultant grayscale distribution for column 100, (c) resultant grayscale distribution for column 300, and (d) segmentation with threshold = 2.

Grahic Jump Location
Figure 17

Filtered segmentation (a) filtered image, (b) left half of the filtered image, and (c) right half of the filtered image.

Grahic Jump Location
Figure 18

The clustering process of the right half image

Grahic Jump Location
Figure 19

The clustering process of the left half image

Grahic Jump Location
Figure 20

Model fitting of laser lines (a) segmented laser lines, (b) fitted model, and (c) fitted model on segmented laser lines

Grahic Jump Location
Figure 21

Processing results for frame 339

Grahic Jump Location
Figure 22

Processing results for frame 340

Grahic Jump Location
Figure 23

Processing results for frame 341

Grahic Jump Location
Figure 24

Processing results for frame 342

Grahic Jump Location
Figure 25

Processing results for frame 343 with diff3 =  −0.0020; P3(1) = 0.0012

Grahic Jump Location
Figure 26

Processing results for frame 344 with diff4 =  −0.0038 P4(1) = −5.6322 × 10−4



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