Title :
Designing neural networks for manufacturing process control systems
Author :
Messom, C.H. ; Hinde, C.J. ; West, A.A. ; Williams, D.J.
Author_Institution :
Loughborough Univ. of Technol., UK
Abstract :
The design of neural networks for the control of discrete manufacturing processes is addressed. Rather than treating the networks as adaptive black boxes, an architecture that links the weights associated with the nodes and thus allows the relationships and internal structure to be tightly constrained is introduced. The constrained search space gives greater confidence in the internal representations that have been induced by the training set and therefore about the correct behavior of the network between the given limits. The method is illustrated by applying it to the dispensing of adhesives
Keywords :
learning (artificial intelligence); neural nets; process computer control; adhesive dispensing; constrained search space; design; discrete manufacturing processes; manufacturing process control; neural networks; nodes; process computer control; Adaptive systems; Computer aided manufacturing; Computer networks; Control systems; Design engineering; Equations; Manufacturing processes; Neural networks; Process control; Pulp manufacturing;
Conference_Titel :
Intelligent Control, 1992., Proceedings of the 1992 IEEE International Symposium on
Conference_Location :
Glasgow
Print_ISBN :
0-7803-0546-9
DOI :
10.1109/ISIC.1992.225128