Approaches to coupling connectionist and expert systems in intelligent manufacturing

Artificial neural networks are successfully applied in different fields of manufacturing, mostly where multisensor integration, robustness, real-timeness, and learning abilities are needed. Since the higher levels of the control and the monitoring hierarchy require symbolic knowledge representation and processing techniques, the integrated use of the symbolic and subsymbolic approaches is straightforward The paper describes two hybrid artificial intelligence systems for control and monitoring of manufacturing processes on different hardware and software bases, The first experiences gained by their usage are outlined. Finally, further possible applications of these hybrid solutions in an intelligent manufacturing environment are enumerated. (C) 1997 Elsevier Science B.V.