Evolutionary adaptation of dispatching agents in heterarchical manufacturing systems

We propose a new approach to job flow adaptive operational control in advan ced manufacturing systems. The major feature of the method is the distribut ion of the control tasks among completely autonomous intelligent agents. Na mely, agents are implicitly coordinated by a nature-analogous adaptation me chanism, which continuously tunes the free parameters of the control law of each agent. The proposed approach is effective and reactive to severe dist urbances and changes in the manufacturing environment. Simulation experimen ts illustrate the operational distributed approach and its response to faul ts.