You are here: Home :: Area NEM :: Engineering :: Automation

Alexander Bollig

Predictive Control with Neural Networks

This paper represents the theoretical background of a model based predictive control scheme developed for closed loop penetration depth control in laser beam welding that optimises the process input laser power by taking the future welding speed into account. For modelling this 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. A possibility to extend the training by local model properties is introduced.

at – Automatisierungstechnik, Oldenbourg Wissenschaftsverlag

Print ISSN: 0178-2312
Volume: 51, 02/2003
Pages: 069

Journal homepage (external site)

Show all available items of this journal

 

Area NEM