ISSN:
1013-9826
Source:
Scientific.Net: Materials Science & Technology / Trans Tech Publications Archiv 1984-2008
Topics:
Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
Notes:
An optical measuring system for the ring test is proposed. In this approach, the machinevision inspection equipment is first built to record and capture the images of ring test from thedigital camcorder.The image processing procedures to detect and locate the edge points of the innerand outer radii in ring convex forming are presented. Unlike the conventional sub-pixel estimationbased on gray-level values, the quantity (8 bits) of color’s scale has been adopted. In imageprocessing procedures, a clustering method called Adaptive Competitive Learning Network(ACLN) is first used to classify the image hues which represent the different heights of bulgeprofiles on the top of ring, and then the edge points can be searched by the interpolation step of subpixelaccuracy. The calibration curves constructed by the mode of non-constant friction factorcalled F-value approach is designed to compare and check with the measurement data. Theexperimental results will be presented and discussed in this study
Type of Medium:
Electronic Resource
URL:
http://www.tib-hannover.de/fulltexts/2011/0528/01/56/transtech_doi~10.4028%252Fwww.scientific.net%252FKEM.364-366.199.pdf
Permalink