Adaptive scheduling and control using artificial neural networks and expert systems for a hierarchical/distributed FMS architecture

Abstract

An adaptive expert scheduler that learns by itself and adapts to the dynamic FMS (flexible manufacturing system) environment was developed. This hybrid system uses a symbiotic architecture composed of expert systems and artificial neural networks and provides a learning scheme guided by past experience. The artificial neural networks recognize patterns in the tasks to be solved in order to select the best scheduling rule according to different criteria. The expert systems, on the other hand, drive the inference strategy and interpret the constraints and restrictions imposed by the upper levels of the control hierarchy of the flexible manufacturing system. The level of self-organization achieved provides a system with a higher probability of success than traditional approaches.<>