Emission analysis of a fluidized bed boiler by using self-organizing maps

Authors:
Mika Liukkonen;Mikko Heikkinen;Eero Hälikkä;Reijo Kuivalainen;Yrjö Hiltunen
Affiliations:
Department of Environmental Science, University of Kuopio, Kuopio, Finland;Department of Environmental Science, University of Kuopio, Kuopio, Finland;Foster Wheeler Power Group, Varkaus, Finland;Foster Wheeler Power Group, Varkaus, Finland;Department of Environmental Science, University of Kuopio, Kuopio, Finland
Venue:
ICANNGA'09 Proceedings of the 9th international conference on Adaptive and natural computing algorithms
Year:
2009

Citing 8
Cited 3

Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Neural Smithing: Supervised Learning in Feedforward Artificial Neural Networks

Neural Smithing: Supervised Learning in Feedforward Artificial Neural Networks
Self-Organizing Maps

Self-Organizing Maps
Applications of Neural Networks and Other Learning Technologies in Process Engineering

Applications of Neural Networks and Other Learning Technologies in Process Engineering
Electronics Process Technology: Production Modelling, Simulation and Optimisation

Electronics Process Technology: Production Modelling, Simulation and Optimisation
Process Monitoring and Modeling Using the Self-Organizing Map

Integrated Computer-Aided Engineering
Application of self-organizing maps in analysis of wave soldering process

Expert Systems with Applications: An International Journal
SOM-Based method for process state monitoring and optimization in fluidized bed energy plant

ICANN'05 Proceedings of the 15th international conference on Artificial Neural Networks: biological Inspirations - Volume Part I

Modeling of the fluidized bed combustion process and NOx emissions using self-organizing maps: An application to the diagnosis of process states

Environmental Modelling & Software
Analysis of flue gas emission data from fluidized bed combustion using self-organizing maps

Applied Computational Intelligence and Soft Computing
Expert system for analysis of quality in production of electronics

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this study, a self-organizing map (SOM) -based process analysis and parameter approximation method was used to the emission analysis of a circulating fluidized bed process. The aim was to obtain the optimal process parameters in respect to the flue gas nitrogen oxide (NOx) content in different predefined states of process. The data processing procedure in the research went as follows. First, the process data were processed by using a self-organizing map and k-means clustering to generate subsets representing the separate process states in the boiler. These process states represent the higher level process conditions in the combustion, and can include for example start-ups, shutdowns, and idle times in addition to the normal process flow. Next, optimal areas were discovered from the map within each process state, and the reference vectors of the optimal neurons were used to approximate the values of desired process parameters. In addition, a subtraction analysis of reference vectors was performed to analyze the optimal situations. In conclusion, the method showed potential considering its wider use in the field of energy production.