Title :
Deformed lattice analysing using neural networks
Author :
Leopold, Jürgen ; Günther, Holger
Author_Institution :
Gessellschaft fur Fertigungtech. und Entwicklung e.V., Tech. Univ. Chemnitz, Germany
fDate :
27 Jun-2 Jul 1994
Abstract :
The image analysis of deformed grids may help for development and investigation of pairs of workpiece and cutting material, optimised technological conditions and new tool material which may allow cutting without coolants and lubricants or with less use of coolants and lubricants. However, for a comprehensive and economical industrial use of these methods it is necessary to automate the recognition of grid points and the analysis of deformations. For the processing of given points there exist some programs and software systems like the system VISIO, developed by the Society for Production Engineering and Development (GFE) Chemnitz, but the analysis of large or extremely deformed grid structures continues to be only practicable manually (using microscopes,digitizers etc.). The paper proposes a solution for recognising points in large deformed and damaged lattices using digital image processing in combination with neural networks
Keywords :
cutting; image processing; learning (artificial intelligence); metalworking; neural nets; plastic deformation; quality control; cutting material; deformed lattice analysis; digital image processing; grid points recognition; neural networks; workpiece; Coolants; Image analysis; Image recognition; Industrial economics; Lattices; Lubricants; Microscopy; Neural networks; Production engineering; Software systems;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374727
