Founded in 1971 >
Chinese Sci-tech Core Periodicals >
British Science Abstracts (SA, INSPEC) Indexed Journals >
United States, Cambridge Scientific Abstract: Technology (CSA: T) Indexed Journals >
United States, Ulrich's Periodicals Directory(UPD)Indexed Journals >
United States, Cambridge Scientific Abstract: Natural Science (CSA: NS) Indexed Journals >
Poland ,Index of Copernicus(IC) Indexed Journals >
International Standard Serial Number:
ISSN 1001-4551
Sponsor:
Zhejiang University;
Zhejiang Machinery and Electrical Group
Edited by:
Editorial of Journal of Mechanical & Electrical Engineering
Chief Editor:
ZHAO Qun
Vice Chief Editor:
TANG ren-zhong,
LUO Xiang-yang
Tel:
86-571-87041360,87239525
Fax:
86-571-87239571
Add:
No.9 Gaoguannong,Daxue Road,Hangzhou,China
P.C:
310009
E-mail:
meem_contribute@163.com
CHEN Zhiqiang, LOU Peihuang, QIAN Xiaoming
(College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China)
Abstract: Aiming at the online quality inspection of welded silicon battery chips, an online quality inspection method of welded silicon battery chips based on visual identification technology was proposed in this paper, including feature recognition and visual measurement. In the feature recognition stage, an improved region growing algorithm was proposed to finish the highspeed and stable detection of gridlinefracture features; For the scratch and dirty features caused by welding, the regions of interest was adaptive thresholded, then the defects were filtered by invariant moments feature. In the field of visual measurement, using the symmetry of target image, pixel based measurements of solder strip offsets and chip spacings were carried out through a number of sampling rectangles. The acquisition of inter chip images at each transmission beat was enabled, the original image was segmented into a number of regions of interest by the edge location method,so that highspeed online detection was completed. The results of actual online test indicate that, the visual inspection method of welded silicon battery chips can identify target defects quickly and accurately, and it has the characteristics of good recognition stability.
Key words: automated welding; online inspection;visual measurement; invariant moments feature; region growing