A blackboard architecture for model-based reasoning and plan refinement in real-time process control

Abstract This article presents an architecture of a model-based and knowledge-based system for real-time supervisory control of chemical process systems. This architecture incorporates the following key features: (1) a temporal reasoning strategy based on time-stamped data arriving from the process; (2) the use of an on-line process model to assist in the decision-making process; (3) a blackboard system for the communication between various knowledge sources; (4) a meta-level decision maker to coordinate the action of these knowledge sources in an orderly and priority-driven fashion, and (5) the concept of continued operational plan refinement to meet the overall goals of the process operation in the presence of continuously changing external environmental stimuli. The proposed architecture has been implemented using an object-oriented programming environment offered through extensions to the C language. Some results on application to the control of an autoclave curing process are given in this paper. The main contribution of this paper is a layout of the system architecture and a demonstration of the advantages resulting from the integration of traditional knowledge-based control implemented using expert operators with model-based control that utilize a simulation model of the process.