Modeling approach to coal gasification using hybrid neural networks

Bing Guo, Youting Shen

Research output: Contribution to journalArticle

Abstract

Coal gasification was carried out in a bench-scale fluidized bed gasifier. The gasifier operated at atmospheric pressure with steam as fluidizing medium. The background of this study was the gas-steam cogeneration system. A hybrid neural network model was synthesized to predict the gas production rates. The model consists of a first principle partial model and a neural network parameter estimator. The model was trained with the experimental gasification data of Jincheng anthracite coal. The model has a good performance of process simulation. A parameter called 'fraction of active char' was proposed in the model. Neural network performed identification of this parameter and obtained its variation with temperature, with respect to Jincheng anthracite.

Original languageEnglish
Pages (from-to)11-15
Number of pages5
JournalQinghua Daxue Xuebao/Journal of Tsinghua University
Volume37
Issue number2
Publication statusPublished - Feb 1997
Externally publishedYes

Fingerprint

Coal gasification
Neural Networks
Neural networks
Modeling
Anthracite
Steam
Fluidized Bed
Model
Process Simulation
First-principles
Neural Network Model
Fluidization
Gases
Gasification
Fluidized beds
Atmospheric pressure
Experimental Data
Identification (control systems)
Estimator
Partial

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Modeling approach to coal gasification using hybrid neural networks. / Guo, Bing; Shen, Youting.

In: Qinghua Daxue Xuebao/Journal of Tsinghua University, Vol. 37, No. 2, 02.1997, p. 11-15.

Research output: Contribution to journalArticle

@article{79eb38a18deb451db6bb8ebf9f6ddbfb,
title = "Modeling approach to coal gasification using hybrid neural networks",
abstract = "Coal gasification was carried out in a bench-scale fluidized bed gasifier. The gasifier operated at atmospheric pressure with steam as fluidizing medium. The background of this study was the gas-steam cogeneration system. A hybrid neural network model was synthesized to predict the gas production rates. The model consists of a first principle partial model and a neural network parameter estimator. The model was trained with the experimental gasification data of Jincheng anthracite coal. The model has a good performance of process simulation. A parameter called 'fraction of active char' was proposed in the model. Neural network performed identification of this parameter and obtained its variation with temperature, with respect to Jincheng anthracite.",
author = "Bing Guo and Youting Shen",
year = "1997",
month = "2",
language = "English",
volume = "37",
pages = "11--15",
journal = "Qinghua Daxue Xuebao/Journal of Tsinghua University",
issn = "1000-0054",
publisher = "Press of Tsinghua University",
number = "2",

}

TY - JOUR

T1 - Modeling approach to coal gasification using hybrid neural networks

AU - Guo, Bing

AU - Shen, Youting

PY - 1997/2

Y1 - 1997/2

N2 - Coal gasification was carried out in a bench-scale fluidized bed gasifier. The gasifier operated at atmospheric pressure with steam as fluidizing medium. The background of this study was the gas-steam cogeneration system. A hybrid neural network model was synthesized to predict the gas production rates. The model consists of a first principle partial model and a neural network parameter estimator. The model was trained with the experimental gasification data of Jincheng anthracite coal. The model has a good performance of process simulation. A parameter called 'fraction of active char' was proposed in the model. Neural network performed identification of this parameter and obtained its variation with temperature, with respect to Jincheng anthracite.

AB - Coal gasification was carried out in a bench-scale fluidized bed gasifier. The gasifier operated at atmospheric pressure with steam as fluidizing medium. The background of this study was the gas-steam cogeneration system. A hybrid neural network model was synthesized to predict the gas production rates. The model consists of a first principle partial model and a neural network parameter estimator. The model was trained with the experimental gasification data of Jincheng anthracite coal. The model has a good performance of process simulation. A parameter called 'fraction of active char' was proposed in the model. Neural network performed identification of this parameter and obtained its variation with temperature, with respect to Jincheng anthracite.

UR - http://www.scopus.com/inward/record.url?scp=0031073456&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031073456&partnerID=8YFLogxK

M3 - Article

VL - 37

SP - 11

EP - 15

JO - Qinghua Daxue Xuebao/Journal of Tsinghua University

JF - Qinghua Daxue Xuebao/Journal of Tsinghua University

SN - 1000-0054

IS - 2

ER -