Operating an FMC by a decision-tree-based adaptive production control system

Abstract

In previous works decision tree mechanisms were suggested for real-time production control of flexible manufacturing systems operating in a constant mix environment. The current paper tests the performance of a decision-treebased adaptive production control system operating in a flexible manufacturing cell in more random environments. A decision-tree-based production control system, which periodically chooses, on the basis of the current state of the system, the most appropriate scheduling rule, out of several predetermined ones, is presented. The performance of the decision-tree-based production control system was tested by simulating a flexible manufacturing cell operating in two different operational environments, distinct by the variability of their demand. The decision tree-based-production control system has performed rather well in the produce-to-order environment. However, it does not outperform the alternative scheduling rules in a highly random produce-to-order environment.