Title :
Development of neural network based plasma monitoring system for laser welding quality analysis
Author :
Kwon, Jangwoo ; Kwon, Osang ; Jan, Younggun ; Lee, Kyoungdon ; Choi, Heungho ; Hong, SeungHong
Author_Institution :
Dept. of Comput. Eng., T.I.T., Pusan, South Korea
Abstract :
Neural networks are shown to be effective in being able to distinguish incomplete penetration-like weld defects by directly analyzing the plasma which is generated on each impingement of the laser on the materials. The performance is similar to that of existing methods based on extracted feature parameters. In each case around 93% of the defects in a database derived from 100 artificially produced defects of known types can be placed into one of two classes: incomplete penetration and bubbling. The present method based on classification using plasma is faster, and the speed is sufficient to allow on-line classification during data collection
Keywords :
feature extraction; image classification; laser beam welding; multilayer perceptrons; plasma diagnostics; plasma production by laser; artificially produced defects; bubbling; classification methods; data collection; database; extracted feature parameters; incomplete penetration-like weld defects; laser welding quality analysis; multilayer perceptron; neural network based plasma monitoring system; neural network classifiers; on-line classification; optical technique; performance; plasma detection; Biomedical computing; Data mining; Feature extraction; Humans; Laser theory; Monitoring; Neural networks; Plasma materials processing; Plasma measurements; Plasma welding;
Conference_Titel :
TENCON 99. Proceedings of the IEEE Region 10 Conference
Conference_Location :
Cheju Island
Print_ISBN :
0-7803-5739-6
DOI :
10.1109/TENCON.1999.818505
