KNOWLEDGE-BASED PROCESS-CONTROL SUPERVISION AND DIAGNOSIS - THE AEROLID APPROACH

The artificial intelligence incidence in process control, although an active area in the researchers community and even with some implementa tions at industrial environment, is not sufficiently evaluated in nume rical terms for the long term. The present article shows such an evalu ation of a knowledge based system, developing supervisory control task s in the sugar production from sugar-beet, and paying particular atten tion to fault detection and diagnosis. A way of conceiving supervision for continuous processes is presented and supported with this industr ial application. The expert system carrying out supervisory tasks oper ates in a VAX(R) workstation, directly over the distributed control sy stem. The expert system development tool is G2(R) which has real-time facilities. Although the core system was developed in G2, it also cons ists of some external modules because it combines both analytical and artificial intelligence problem resolution techniques. The global arch itecture, as well as the implementation details of the modules necessa ry for fault identification, are presented altogether with the experim ental results obtained from the factory field. (C) 1998 Elsevier Scien ce Ltd. All rights reserved.