Using hybrid neural networks/expert systems for intelligent scheduling in flexible manufacturing systems

Summary form only given, as follows. Recent developments in computer technology and increasingly sophisticated applications of artificial intelligence (AI) have made possible a greater level of intelligence within flexible manufacturing systems (FMS) and, in particular, the scheduling of these systems. An intelligent scheduling system is presented for FMS that makes use of the integration of two AI technologies. These two AI technologies-neural networks and expert systems-provide the intelligence that the scheduling function requires in order to generate good schedules within the restrictions imposed by real-time problems. Because the system has the ability to plan ahead and learn, it has a higher probability of success than conventional approaches. In addition, it has the ability to ´self-improve´ in the event of a performance failure.<>