Application of neuro-fuzzy identifier for a fossil fuel boiler system

Author

Ghezelayagh, Hamid ; Lee, Kwang Y.

Author_Institution

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

Volume

2

fYear

2000

fDate

2000

Firstpage

1135

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 from the experimental boiler data. The interconnections of neuro-fuzzy layers furnish these fuzzy rules. A genetic algorithm (GA) trains the neuro-fuzzy identifier and extracts the linguistic rules from measured boiler data. GA training takes the advantages of nonbinary alphabet and compound chromosomes to train the multi-input multi-output (MIMO) neuro-fuzzy identifier. The fuzzy membership functions need to be adjusted during the training to minimize the identifier response error. Error back-propagation training methodology is chosen to tune the membership function parameters. The identifier response is investigated in several operating points. This neuro-fuzzy identifier is implemented within an object oriented programming tool that provides portability of the identification process. Therefore, it is a strong candidate to substitute model-based identifiers in applications such as model reference control system or predictive control problem to reduce the required design time

Keywords

MIMO systems; backpropagation; boilers; feedforward neural nets; fuzzy neural nets; fuzzy set theory; genetic algorithms; object-oriented programming; parameter estimation; power engineering computing; MIMO neuro-fuzzy identifier training; boiler dynamics; compound chromosomes; drum type boiler identification; error back-propagation training; feedforward neural net; fossil fuel boiler system; fuzzy membership functions; fuzzy rules; genetic algorithm; identification process; identifier response error minimisation; linguistic rules; measured boiler data; membership function parameters tuning; model reference control system; multi-input multi-output neuro-fuzzy identifier; multi-layer neuro-fuzzy system; neuro-fuzzy identifier; neuro-fuzzy layers; nonbinary alphabet; object oriented programming tool; predictive control; rule-based approach; Biological cells; Boilers; Data mining; Fossil fuels; Fuzzy neural networks; Genetic algorithms; MIMO; Object oriented modeling; Object oriented programming; Predictive models;

fLanguage

English

Publisher

ieee

Conference_Titel

Power Engineering Society Winter Meeting, 2000. IEEE

Print_ISBN

0-7803-5935-6

Type

conf

DOI

10.1109/PESW.2000.850100

Filename

850100