Integrated environment for intelligent control

A new architecture for designing real-time intelligent control systems is developed, which consists of several symbolic reasoning systems, numerical computation routines and a meta-system to control the selection, operation and communication of these programs. The key issue to construct such an integrated intelligent system is to organize a meta-system. Briefly, the main functions of the meta-system are: (I) To coordinate and manage all symbolic reasoning systems and numerical computation routines in the integrated intelligent system; (2) To distribute knowledge into separate expert systems and numerical routines so that the integrated intelligent system can be managed effectively; (3) To acquire new knowledge; (4) To find an optimal solution for the conflict facts and events among different expert systems; (5) To provide the possibility of parallel processing in the integrated intelligent system; (6) To communicate with the measuring devices and the final control element in the control system. The meta-system is implemented with a Lisp-like language on a VAX 11/780 computer under UNIX environment. The configuration of the real-time intelligent control system has attracted significant attention from both the industry and the academia and is expected to lead to a new era for the applications of AI technique to chemical and process engineering.