Ky. Bae et Sj. Na, A STUDY OF VISION-BASED MEASUREMENT OF WELD JOINT SHAPE INCORPORATINGTHE NEURAL-NETWORK, Proceedings of the Institution of Mechanical Engineers. Part B, Journal of engineering manufacture, 208(1), 1994, pp. 61-69
Visual sensing of the surface geometry is often necessary to inspect a
nd evaluate the quality of welded joints as well as to sense the trans
ient distortion of a structure during welding for the feedback of its
current geometry. This investigation presents a simple and non-contact
digitization method of the vision-based system for measuring the thre
e-dimensional surface geometry of the object distorted by welding. Its
basic principles are based on the equation derived from the geometric
optics, for which the illumination of the laser beam was controlled i
n the form of the projected plane. This method utilized a 10 mW He-Ne
laser for the structured light and a charge coupled device (CCD) camer
a as the vision sensor. When the laser stripe is projected on to the w
eldment, a minute deviation from the perfect plane existing on the spe
cimen surface causes a distortion of the stripe. The shape and amount
of the weldment distortion can be then calculated by analysing the dis
torted laser stripe. In this study, a neural network was proposed and
implemented for recognizing the laser stripe features from the image p
lane. A calibration scheme of corresponding an image to the world posi
tion was also adopted for determining the sectional features of the we
lding distortion. The feasibility of determining the welding distortio
n by the proposed vision-based system was demonstrated through the exp
eriments with various types of specimen.