Title :
Prediction of the laser sheet bending using neural network
Author :
Dragos, Valentina ; Dan, V. ; Kovacevic, Radovan
Author_Institution :
Dept. of Mech. Eng., Southern Methodist Univ., Dallas, TX
Abstract :
In this paper, a neural network algorithm is used in predicting the future shape obtained by laser forming. Aluminum and steel samples were used and the thickness of the materials, the laser power beam and the scanning speed were the variable parameters of the process. The bending angles versus the number of scanning passes obtained experimentally are in good agreement with angle values given by the training process algorithm
Keywords :
bending; feedforward neural nets; forming processes; laser beam machining; metalworking; neurocontrollers; bending angles; laser forming; laser power beam; laser sheet bending; material thickness; neural network algorithm; scanning passes; scanning speed; training process algorithm; variable parameters; Aluminum; Building materials; Laser beams; Neural networks; Optical materials; Power lasers; Shape; Sheet materials; Steel; Structural beams;
Conference_Titel :
Circuits and Systems, 2000. Proceedings. ISCAS 2000 Geneva. The 2000 IEEE International Symposium on
Conference_Location :
Geneva
Print_ISBN :
0-7803-5482-6
DOI :
10.1109/ISCAS.2000.856153
