Automatic Generation a Net of Models for High and Low Levels of Production Control
Abstract
The paper presents two applications of the novel, artificial neural network (ANN) and feature selection based combined, dynamic technique to automatically dissolve a large, complex system into a net of connected sub-models. The first application is a solution for the lower level of customised mass-production systems, for increasing their productivity. The second one is a concept for the identification and reorganisation of manufacturing agents, based on simulation experience. The main idea behind, is to give the learning capability to agents already at their definition phase, and to maximise their foresight power.
