engleski

Application of modified ART 1 neural network for solving cell formation

In order to achieve high productivity under the turbulent production environment, production systems have been changed into cellular manufacturing systems. That involves dividing of production system into some cells by collecting similar products and machines. In this paper, a neural network approach for solving cell formation problem is investigated. We modify the binary self-organizing neural network algorithm (ART 1) by changing the weith vector, updating equation, and using a set of supplementary procedures. Comparing of grouping efficiency with some other well-known approaches shows the effectiveness of the proposed algorithm.

neural network; cellular manufacturing; grouping efficiency

nije evidentirano