The potential of neural networks is examined, and the effect of parallel processing on the solution of the stock-cutting problem is assessed. The conceptual model proposed integrates a feature-recognition network and a simulated annealing approach. The model uses a neocognitron neural network paradigm to generate data for assessing the degree of match between two irregular patterns. The information generated through the feature recognition network is passed to an energy function, and the optimal configuration of patterns is computed using a simulated annealing algorithm. Basics of the approach are demonstrated with an example.
C. H. Dagli, "Neural Networks in Manufacturing: Possible Impacts on Cutting Stock Problems," Proceedings of Rensselaer's Second International Conference on Computer Integrated Manufacturing, 1990, Institute of Electrical and Electronics Engineers (IEEE), Jan 1990.
The definitive version is available at https://doi.org/10.1109/CIM.1990.128157
Rensselaer's Second International Conference on Computer Integrated Manufacturing, 1990
Engineering Management and Systems Engineering
Keywords and Phrases
Computerised Pattern Recognition; Cutting Stock Problems; Feature-Recognition Network; Manufacturing; Manufacturing Data Processing; Neural Nets; Neural Networks; Parallel Processing; Production Control; Simulated Annealing; Stock Control
Article - Conference proceedings
© 1990 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.