Neural networks implementation for modeling and control design of manufacturing systems

This paper presents a dynamic neural network implementation for the modelin g and control design of a class of manufacturing systems. The evolution of the considered systems is supposed to be continuous and non-stochastic. A s eparate implementation of the system elements is detailed. These elements a re then connected together in order to obtain a global net that simulates t he behavior of the real system. The obtained model is modular and can be ad apted easily for any modification of the system. Permanent correction rules are developed to control the speed of the machines according to a desired profile and to take into consideration the buffers limited capacities. The convergence of the control design is proved. The proposed approach is appli ed on an exhaust valves assembly workshop.