Concept for combining features of real-time and expert systems for on-line plant diagnosis

Author

Kern, Heinrich ; Fathi-Torbaghan, Madjid

Author_Institution

Inst. of Mater. Technol., Dortmund Univ., West Germany

fYear

1990

fDate

21-23 Mar 1990

Firstpage

803

Lastpage

807

Abstract

A description is presented of an AI implementation in an industrial power plant: malfunction diagnosis based on the evaluation of plant performance. It is intended to support the development and maintenance of a knowledge-based real-time control system. The features of a programming tool which combines characteristics of expert systems and real-time supervision systems are explained. The system is used for online diagnosis of a plant. The real-time properties are achieved by dividing data processing into several processing units which are computed in parallel. Since plant diagnosis differs from most expert system applications, the expert system part has been developed with regard to this. A prototype of this system has been implemented for the domain of thermal spraying

Keywords

expert systems; power station computer control; real-time systems; artificial intelligence implementation; expert systems; industrial power plant; knowledge-based real-time control system; malfunction diagnosis; on-line plant diagnosis; online diagnosis; programming tool; prototype; real time systems; thermal spraying; Artificial intelligence; Concurrent computing; Control systems; Data processing; Diagnostic expert systems; Electrical equipment industry; Expert systems; Power generation; Real time systems; Thermal spraying;

fLanguage

English

Publisher

ieee

Conference_Titel

Computers and Communications, 1990. Conference Proceedings., Ninth Annual International Phoenix Conference on

Conference_Location

Scottsdale, AZ

Print_ISBN

0-8186-2030-7

Type

conf

DOI

10.1109/PCCC.1990.101701

Filename

101701