NOx and CO prediction in fossil fuel plants by time delay neural networks

Tülay Adali, Bora Bakal, Mustafa (Kemal) Sonmez, Reza Fakory

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

This paper presents a time delay neural network (TDNN) model designed for the prediction of nitrogen oxides (NOx) and carbon monoxide (CO) emissions from a fossil fuel power plant. NOx and CO emissions of the plant are determined as a function of other related time-series such as air flow rates and oxygen levels that are measured during the system operation. Correlation analysis is performed on the data to determine the location and the spread of cross-correlation between pairs of variables and this information is used to form a variable tapped delay line at the input of the network. We also introduce a neural network based preprocessor which employs an iterative regularization scheme to recover missing portions of CO data that are censored due to saturation of the measuring device. Prediction after training with the restored data set is observed to be significantly more accurate.

Original languageEnglish (US)
Pages (from-to)27-39
Number of pages13
JournalIntegrated Computer-Aided Engineering
Volume6
Issue number1
StatePublished - 1999
Externally publishedYes

Fingerprint

Carbon Monoxide
Nitrogen oxides
Fossil fuels
Carbon monoxide
Nitrogen
Oxides
Time Delay
Time delay
Neural Networks
Neural networks
Prediction
Fossil fuel power plants
Iterative Regularization
Variable Delay
Delay Line
Correlation Analysis
Electric delay lines
Power Plant
Cross-correlation
Neural Network Model

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Computer Science Applications
  • Engineering (miscellaneous)

Cite this

Adali, T., Bakal, B., Sonmez, M. K., & Fakory, R. (1999). NOx and CO prediction in fossil fuel plants by time delay neural networks. Integrated Computer-Aided Engineering, 6(1), 27-39.

NOx and CO prediction in fossil fuel plants by time delay neural networks. / Adali, Tülay; Bakal, Bora; Sonmez, Mustafa (Kemal); Fakory, Reza.

In: Integrated Computer-Aided Engineering, Vol. 6, No. 1, 1999, p. 27-39.

Research output: Contribution to journalArticle

Adali, T, Bakal, B, Sonmez, MK & Fakory, R 1999, 'NOx and CO prediction in fossil fuel plants by time delay neural networks', Integrated Computer-Aided Engineering, vol. 6, no. 1, pp. 27-39.
Adali, Tülay ; Bakal, Bora ; Sonmez, Mustafa (Kemal) ; Fakory, Reza. / NOx and CO prediction in fossil fuel plants by time delay neural networks. In: Integrated Computer-Aided Engineering. 1999 ; Vol. 6, No. 1. pp. 27-39.
@article{b6d4f5698ed54836be99b05dfde3894b,
title = "NOx and CO prediction in fossil fuel plants by time delay neural networks",
abstract = "This paper presents a time delay neural network (TDNN) model designed for the prediction of nitrogen oxides (NOx) and carbon monoxide (CO) emissions from a fossil fuel power plant. NOx and CO emissions of the plant are determined as a function of other related time-series such as air flow rates and oxygen levels that are measured during the system operation. Correlation analysis is performed on the data to determine the location and the spread of cross-correlation between pairs of variables and this information is used to form a variable tapped delay line at the input of the network. We also introduce a neural network based preprocessor which employs an iterative regularization scheme to recover missing portions of CO data that are censored due to saturation of the measuring device. Prediction after training with the restored data set is observed to be significantly more accurate.",
author = "T{\"u}lay Adali and Bora Bakal and Sonmez, {Mustafa (Kemal)} and Reza Fakory",
year = "1999",
language = "English (US)",
volume = "6",
pages = "27--39",
journal = "Integrated Computer-Aided Engineering",
issn = "1069-2509",
publisher = "IOS Press",
number = "1",

}

TY - JOUR

T1 - NOx and CO prediction in fossil fuel plants by time delay neural networks

AU - Adali, Tülay

AU - Bakal, Bora

AU - Sonmez, Mustafa (Kemal)

AU - Fakory, Reza

PY - 1999

Y1 - 1999

N2 - This paper presents a time delay neural network (TDNN) model designed for the prediction of nitrogen oxides (NOx) and carbon monoxide (CO) emissions from a fossil fuel power plant. NOx and CO emissions of the plant are determined as a function of other related time-series such as air flow rates and oxygen levels that are measured during the system operation. Correlation analysis is performed on the data to determine the location and the spread of cross-correlation between pairs of variables and this information is used to form a variable tapped delay line at the input of the network. We also introduce a neural network based preprocessor which employs an iterative regularization scheme to recover missing portions of CO data that are censored due to saturation of the measuring device. Prediction after training with the restored data set is observed to be significantly more accurate.

AB - This paper presents a time delay neural network (TDNN) model designed for the prediction of nitrogen oxides (NOx) and carbon monoxide (CO) emissions from a fossil fuel power plant. NOx and CO emissions of the plant are determined as a function of other related time-series such as air flow rates and oxygen levels that are measured during the system operation. Correlation analysis is performed on the data to determine the location and the spread of cross-correlation between pairs of variables and this information is used to form a variable tapped delay line at the input of the network. We also introduce a neural network based preprocessor which employs an iterative regularization scheme to recover missing portions of CO data that are censored due to saturation of the measuring device. Prediction after training with the restored data set is observed to be significantly more accurate.

UR - http://www.scopus.com/inward/record.url?scp=0032715984&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032715984&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0032715984

VL - 6

SP - 27

EP - 39

JO - Integrated Computer-Aided Engineering

JF - Integrated Computer-Aided Engineering

SN - 1069-2509

IS - 1

ER -