SYNTHETIC DISCRIMINANT WIENER FILTER FOR IN-PROCESS LASER CUTTING QUALITY-CONTROL

Authors
Citation
Cr. Chatwin, SYNTHETIC DISCRIMINANT WIENER FILTER FOR IN-PROCESS LASER CUTTING QUALITY-CONTROL, Integrated computer-aided engineering, 3(2), 1996, pp. 129-138
Citations number
11
Categorie Soggetti
Computer Application, Chemistry & Engineering","Computer Science Artificial Intelligence",Engineering,"Computer Science Interdisciplinary Applications
ISSN journal
10692509
Volume
3
Issue
2
Year of publication
1996
Pages
129 - 138
Database
ISI
SICI code
1069-2509(1996)3:2<129:SDWFFI>2.0.ZU;2-A
Abstract
Characteristic spark-cone images are produced beneath the workpiece du ring reactive gas assisted laser cutting processes. Laser cutting qual ity is controlled using robust optical pattern recognition and classif ication of the spark-cone images. High irradiance fully formed spark c ones are characteristic of a high quality dress-free cut, whereas a sp arse cone indicates a poor quality cut with dress attachment to the lo wer surface of the workpiece. It was found that by incorporating both the out-of-class image, sparse spark cone, and the in-class image, ful ly formed spark cone into a Wiener filter construction, the discrimina nt ability of the imaging control system was significantly enhanced; t hree out-of-class images gave optimum performance. The Wiener filters formed from spark-cone images. recorded when cutting different thickne ss materials, were integrated into a synthetic discriminant function ( SDF) filter. When spark-cone images of a laser cutting process were cr oss-correlated with the SDF, it gave high output peaks for a good qual ity cut, and a low output signal for a poor quality cut (Lugt, 1994; W ang, Chatwin, and Young, 1994; Braunecker, Hauk, and Lohmann, 1979; Ca sasent, 1984; Huang and Chatwin, 1994). (C) 1996 John Wiley & Sons, In c.