Training neuro-fuzzy boiler identifier with genetic algorithm and error back-propagation

Author

Ghezelayagh, Hamid ; Lee, Kwang Y.

Author_Institution

Dept. of Electr. Eng., Pennsylvania State Univ., University Park, PA, USA

Volume

2

fYear

1999

fDate

1999

Firstpage

978

Abstract

A multi-layer neuro-fuzzy system presents identification of a drum type boiler. This identification provides a rule-based approach to approximate the boiler dynamics. The interconnections of neuro-fuzzy layers furnish these fuzzy rules. A genetic algorithm (GA) trains the neuro-fuzzy identifier and extracts the linguistic fuzzy rules from measured boiler data. This GA training takes the advantages of nonbinary alphabet and compound chromosomes to train the neuro-fuzzy identifier. An error backpropagation training methodology is chosen to tune the membership function parameters. This neuro-fuzzy identifier obtains time response similar to boiler model while it avoids mathematical complexity of model dynamics

Keywords

backpropagation; boilers; control system synthesis; fuzzy control; fuzzy neural nets; genetic algorithms; identification; neurocontrollers; optimal control; power station control; steam power stations; compound chromosomes; drum type boiler; error backpropagation training methodology; fuzzy rules; genetic algorithm; linguistic fuzzy rules; mathematical complexity; membership function parameters tuning; neuro-fuzzy boiler identifier; nonbinary alphabet; steam power plant control; time response; Artificial neural networks; Biological cells; Boilers; Data mining; Fuzzy logic; Fuzzy neural networks; Genetic algorithms; Mathematical model; Multi-layer neural network; Neurons;

fLanguage

English

Publisher

ieee

Conference_Titel

Power Engineering Society Summer Meeting, 1999. IEEE

Conference_Location

Edmonton, Alta.

Print_ISBN

0-7803-5569-5

Type

conf

DOI

10.1109/PESS.1999.787449

Filename

787449