Automotive airbag assembly quality visual inspection method studies based on MATLAB

Author

Shi Xianjiang ; Zhao Yue ; Song Peng ; Sun Han ; Ling Xiaohui ; Wang Andong

Author_Institution

Mech. & Power Eng. Coll., Harbin Univ. of Sci. & Technol., Harbin, China

fYear

2012

fDate

29-31 Dec. 2012

Firstpage

1225

Lastpage

1228

Abstract

Based on BP artificial neural network, a method for the recognition of buckle which connect the airbag gas generator brackets and decorative cover is discussed in this paper. First, MATLAB is applied for image binarization and edge extraction. Then extract linear feature of the edge by using Hough transform. Finally, BP neural network is applied for image recognition and classification. It is demonstrated by practice that this method can be used for fast and efficient recognition of completely fasten buckle and incompletely fasten buckle with high accuracy and practical value.

Keywords

Hough transforms; assembling; automobile manufacture; automotive components; backpropagation; edge detection; feature extraction; image classification; inspection; neural nets; production engineering computing; BP artificial neural network; Hough transform; MATLAB; airbag gas generator brackets; automotive airbag assembly; backpropagation; buckle recognition; decorative cover; edge extraction; image binarization; image classification; image recognition; linear feature extraction; quality visual inspection method; BP neural network; MATLAB; aairbag; image recognition; sssembly quality;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Science and Network Technology (ICCSNT), 2012 2nd International Conference on

Conference_Location

Changchun

Print_ISBN

978-1-4673-2963-7

Type

conf

DOI

10.1109/ICCSNT.2012.6526145

Filename

6526145