A methodological approach to multisensor classification for innovative laser material processing units

Online quality detection and online laser beam control are important research topics to improve the overall quality of presentday laser beam material processing units. In both cases innovative units are being studied where the state is monitored by a set of heterogeneous in-process sensors conveying a large amount of information. However, low experimental reproducibility, lack of dominion knowledge and high costs greatly limit our ability to find an optimal solution. In this paper we propose a methodology to guide the engineer's design choices towards an optimal implementation of the inductive classifier.

[1]  A. I. Gavrilov.  Development of automatic control system for laser welding using neural network technology , 1998 .

[2]  Keinosuke Fukunaga,et al.  Introduction to Statistical Pattern Recognition , 1972 .

[3]  Aapo Hyvärinen,et al.  Survey on Independent Component Analysis , 1999 .

[4]  V. E. Merchant,et al.  Laser welding in the pipeline industry , 1992 .

[5]  J. Makhoul.  Pattern recognition properties of neural networks , 1991, Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop.

[6]  Seiichiro Kimura,et al.  Quality monitoring technology for laser welding , 1995, Proceedings of IECON '95 - 21st Annual Conference on IEEE Industrial Electronics.

[7]  Gregory L. Plett,et al.  Specification for common IEEE styles , 1997 .

[8]  H.-A. Crostack,et al.  Non-destructive evaluation of seams of laser welded tools using the CS-eddy current technique , 1998, IECON '98. Proceedings of the 24th Annual Conference of the IEEE Industrial Electronics Society (Cat. No.98CH36200).

[9]  A Hyvarinen,et al.  SURVEY OF INDEPENDENT COMPONENT ANALYSIS , 1999 .

[10]  D. F. Farson,et al.  Classification of laser welds by acoustic signature , 1990, 29th IEEE Conference on Decision and Control.

[11]  B. Everitt,et al.  Applied Multivariate Data Analysis. , 1993 .

[12]  Robert I. Damper,et al.  Implementing the k-nearest neighbour rule via a neural network , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.