A multiobjective optimisation system for a glass furnace

Author

Pina, Joao ; Lima, Pedro

Author_Institution

Inst. Super. Tecnico, Lisbon, Portugal

fYear

1999

fDate

Aug. 31 1999-Sept. 3 1999

Firstpage

3969

Lastpage

3974

Abstract

An Expert Controller (EC) for the Operation of a recuperative glass furnace is introduced in this paper. The EC is part of an Integrated Operation and Control System, whose hierarchical architecture is also described, and is divided in two subsystems, a Fault Detection System, and a Process Optimisation System (POS). The POS architecture and operation, detailed in this paper, is based on a Genetic Algorithm, for solution search, and a learning algorithm, based on fuzzy set theory, to interpolate a cost function, which quantifies one of the objectives.

Keywords

fault diagnosis; furnaces; fuzzy set theory; genetic algorithms; glass manufacture; intelligent control; learning (artificial intelligence); EC; POS architecture; cost function; expert controller; fault detection system; fuzzy set theory; genetic algorithm; integrated operation and control system; learning algorithm; multiobjective optimisation system; process optimisation system; recuperative glass furnace; subsystems; Furnaces; Genetic algorithms; Glass; Optimization; Process control; Sociology; Statistics; Expert control; Pareto optimality; genetic algorithms; glass furnace; multiobjective optimisation;

fLanguage

English

Publisher

ieee

Conference_Titel

Control Conference (ECC), 1999 European

Conference_Location

Karlsruhe

Print_ISBN

978-3-9524173-5-5

Type

conf

Filename

7099952