Learning process in a class of computer integrated manufacturing systems with parametric uncertainties

The paper is concerned with a class of manufacturing processes described by a relational knowledge representation containing unknown parameters. Two kinds of the manufacturing processes with different structures of material and task flow are considered. For these kinds the algorithms of learning and control for the central decision support computer system integrating the manufacturing process are presented. The learning process consists in using the results of step by step knowledge validation and updating to the determination of the current control decisions. The idea of learning described in the paper may be considered as a generalization of the known concept of the adaptive control using the results of current identification. Simple illustrative examples, results of simulations for a simple case and additional remarks concerning related problems are included.