Skip to main navigation Skip to search Skip to main content

On-line fuel tracking by combining principal component analysis and neural network techniques

  • Lijun Xu*
  • , Yong Yan
  • , Steve Cornwell
  • , Gerry Riley
  • *Corresponding author for this work
  • University of Greenwich
  • RWE Power AG

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper presents a novel approach to the on-line tracking of pulverised fuel during combustion. A specially designed flame detector containing three photodiodes is used to derive multiple signals covering a wide spectrum of the flame radiation from the infrared to ultraviolet regions through the visible band. Various flame features are extracted from the time and frequency domains. A back-propagation neural network is deployed to map the flame features to an individual type of fuel. The neural network has incorporated Principal Component Analysis to reduce the complexity of the network and hence its training time. Results obtained from experiments using eight different types of coal on a 0.5MWth combustion test facility demonstrate that the approach is effective for the identification of the type of fuel being fired under steady combustion conditions and the success rate is greater than 93%.

Original languageEnglish
Title of host publicationProceedings of the 21st IEEE Instrumentation and Measurement Technology Conference, IMTC/04
EditorsS. Demidenko, R. Ottoboni, D. Petri, V. Piuri, D.C.T. Weng
Pages1806-1809
Number of pages4
DOIs
StatePublished - 2004
Externally publishedYes
EventProceedings of the 21st IEEE Instrumentation and Measurement Technology Conference, IMTC/04 - Como, Italy
Duration: 18 May 200420 May 2004

Publication series

NameConference Record - IEEE Instrumentation and Measurement Technology Conference
Volume3
ISSN (Print)1091-5281

Conference

ConferenceProceedings of the 21st IEEE Instrumentation and Measurement Technology Conference, IMTC/04
Country/TerritoryItaly
CityComo
Period18/05/0420/05/04

Keywords

  • Combustion efficiency
  • Fuel tracking
  • Neural network
  • Power station
  • Principal component analysis

Fingerprint

Dive into the research topics of 'On-line fuel tracking by combining principal component analysis and neural network techniques'. Together they form a unique fingerprint.

Cite this