Title :
IPCA, an architecture for intelligent control
Author :
Decker, David B. ; Punch, William F. ; Sticklen, Jon
Author_Institution :
Dept. of Comput. Sci., Michigan State Univ., East Lansing, MI, USA
Abstract :
IPCA (Intelligent Process Control Architecture) is an architecture for flexible, intelligent control. IPCA is rooted in the generic task (GT) approach to knowledge-based systems and incorporates plan generation and real-time plan execution monitoring components. The plan generation component produces a state-based process control plan representation which typically contains a collection of possible paths from initial to desired process states. Selection of the precise path taken through the process control plan is determined by a plan execution monitoring component. The plan execution monitor incrementally determines in real time appropriate partial paths through the process control plan based on sensory input gathered from real-time process monitoring. This real-time selection of appropriate plan fragments and control methods contained in the process control plan is facilitated through the use of a sponsor-selector mechanism. The usefulness of this approach to intelligent control is demonstrated by applying the architecture to the control of a microwave-based composite material fabrication process. Experimental results demonstrate the effectiveness of IPCA in this domain
Keywords :
computerised monitoring; intelligent control; monitoring; real-time systems; IPCA; Intelligent Process Control Architecture; flexible intelligent control; generic task approach; knowledge-based systems; microwave-based composite material fabrication process; plan execution monitoring component; plan generation; real-time plan execution monitoring component; sponsor-selector mechanism; state-based process control plan representation; Assembly; Automatic control; Control system synthesis; Control systems; Intelligent control; Libraries; Mobile robots; Process control; Remotely operated vehicles; US Department of Transportation;
Conference_Titel :
Intelligent Control, 1996., Proceedings of the 1996 IEEE International Symposium on
Conference_Location :
Dearborn, MI
Print_ISBN :
0-7803-2978-3
DOI :
10.1109/ISIC.1996.556181