Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Identification and predictive control of laser beam welding using neural networks

: Bollig, A.; Abel, D.; Kratzsch, C.; Kaierle, S.

European Union Control Association -EUCA-; Institution of Electrical Engineers -IEE-, London:
European Control Conference, ECC 2003. CD-ROM : 1 - 4 September, University of Cambridge, UK
Stevenage, Herts.: IEE Event Services, 2003
8 pp.
European Control Conference (ECC) <7, 2003, Cambridge>
Conference Paper
Fraunhofer ILT ()
neural network; predictive control; system identification; linearization; laser beam welding

Welding with laser beams is an innovative technique, which leads to higher penetration depth and a narrower seam compared to conventional welding techniques. One significant criterion of the quality of a junction is the penetration depth. Within this article a predictive control scheme is presented that optimises the process' input laser power by taking the future welding speed into account. For modelling the non-linear process an Artificial Neural Network (ANN) is applied. The GPC-algorithm with a linear model obtained by instantaneous linearization of the network is used. For this reason, an extended training of the ANN is introduced. First results of the application on a real laser welding system are described.