Prediction of the Laser Sheet Bending Using Neural Network

ROMANIAN JOURNAL OF INFORMATION SCIENCE AND TECHNOLOGY
Volume 3, Number 1, 2000, 277 - 286

Prediction of the Laser Sheet Bending
Using Neural Network

Dragos Vasile, Dan Vasile
School of Engineering and Applied Science,
Southern Methodist University
3160 SMU Blvd., PO Box 750337
Dallas, Texas 75272, USA

Dan Stoichescu, Anca Manolescu
School of Electronics and Telecommunication,
Polytechnic University of Bucharest
1-3 Iuliu Maniu Blvd., Sector 6, Bucharest, Romania

Abstract.
The back-propagation algorithm is used to predict the bending angle obtained by laser forming. Aluminum and steel samples were used, and material thickness, laser power and scanning speed are the variables. The experimental relationship between the bending angle and the number of scanning passes agrees well with the relationship predicted by the training process algorithm.