A neural network model in LaNixAl1-xO3 catalyst for methane reforming in SOFC

Sian Jie Ciou, Ya Wun Jhang, Ying Jhih Lai, Kuan-Zong Fung, Min Hsiung Hung, Kai-Wei Chiang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

There has been a great interest in application of SOFC using hydrocarbon fuel, and the major issue associated with the improvement of steam reforming is the possibility to extend the area of operation conditions, and lead to low carbon formation. The improvement can be achieved by modifying the design of existing nickel catalysts. Generally, mathematical modeling can be considered as an important element in the methane reforming in terms of the avoidance of extensive experiments. In this article, a two layered feed-forward neural network has been trained with the back propagation algorithm to learn parameters in the process that the LaNixAl1-xO3(x = 0.1-0.9), reforms methane. The data used during the training procedure are generated by using of mass spectrometer after reforming. The average values of the errors for prediction are well below 5% The artificial neural network (ANN) model was capable of modeling the relationship between catalytic behaviors and the structure of catalytic well.

Original languageEnglish
Title of host publicationECS Transactions - 10th International Symposium on Solid Oxide Fuel Cells, SOFC-X
Pages1929-1937
Number of pages9
Edition1 PART 2
DOIs
Publication statusPublished - 2007 Dec 1
Event10th International Symposium on Solid Oxide Fuel Cells, SOFC-X - , Japan
Duration: 2007 Jun 32007 Jun 8

Publication series

NameECS Transactions
Number1 PART 2
Volume7
ISSN (Print)1938-5862
ISSN (Electronic)1938-6737

Other

Other10th International Symposium on Solid Oxide Fuel Cells, SOFC-X
CountryJapan
Period07-06-0307-06-08

Fingerprint

Reforming reactions
Solid oxide fuel cells (SOFC)
Methane
Neural networks
Catalysts
Backpropagation algorithms
Steam reforming
Feedforward neural networks
Mass spectrometers
Hydrocarbons
Nickel
Carbon
Experiments

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Ciou, S. J., Jhang, Y. W., Lai, Y. J., Fung, K-Z., Hung, M. H., & Chiang, K-W. (2007). A neural network model in LaNixAl1-xO3 catalyst for methane reforming in SOFC. In ECS Transactions - 10th International Symposium on Solid Oxide Fuel Cells, SOFC-X (1 PART 2 ed., pp. 1929-1937). (ECS Transactions; Vol. 7, No. 1 PART 2). https://doi.org/10.1149/1.2729305
Ciou, Sian Jie ; Jhang, Ya Wun ; Lai, Ying Jhih ; Fung, Kuan-Zong ; Hung, Min Hsiung ; Chiang, Kai-Wei. / A neural network model in LaNixAl1-xO3 catalyst for methane reforming in SOFC. ECS Transactions - 10th International Symposium on Solid Oxide Fuel Cells, SOFC-X. 1 PART 2. ed. 2007. pp. 1929-1937 (ECS Transactions; 1 PART 2).
@inproceedings{2b1399d7f8ac4342a8fdab2e0a57c3a7,
title = "A neural network model in LaNixAl1-xO3 catalyst for methane reforming in SOFC",
abstract = "There has been a great interest in application of SOFC using hydrocarbon fuel, and the major issue associated with the improvement of steam reforming is the possibility to extend the area of operation conditions, and lead to low carbon formation. The improvement can be achieved by modifying the design of existing nickel catalysts. Generally, mathematical modeling can be considered as an important element in the methane reforming in terms of the avoidance of extensive experiments. In this article, a two layered feed-forward neural network has been trained with the back propagation algorithm to learn parameters in the process that the LaNixAl1-xO3(x = 0.1-0.9), reforms methane. The data used during the training procedure are generated by using of mass spectrometer after reforming. The average values of the errors for prediction are well below 5{\%} The artificial neural network (ANN) model was capable of modeling the relationship between catalytic behaviors and the structure of catalytic well.",
author = "Ciou, {Sian Jie} and Jhang, {Ya Wun} and Lai, {Ying Jhih} and Kuan-Zong Fung and Hung, {Min Hsiung} and Kai-Wei Chiang",
year = "2007",
month = "12",
day = "1",
doi = "10.1149/1.2729305",
language = "English",
isbn = "9781566775564",
series = "ECS Transactions",
number = "1 PART 2",
pages = "1929--1937",
booktitle = "ECS Transactions - 10th International Symposium on Solid Oxide Fuel Cells, SOFC-X",
edition = "1 PART 2",

}

Ciou, SJ, Jhang, YW, Lai, YJ, Fung, K-Z, Hung, MH & Chiang, K-W 2007, A neural network model in LaNixAl1-xO3 catalyst for methane reforming in SOFC. in ECS Transactions - 10th International Symposium on Solid Oxide Fuel Cells, SOFC-X. 1 PART 2 edn, ECS Transactions, no. 1 PART 2, vol. 7, pp. 1929-1937, 10th International Symposium on Solid Oxide Fuel Cells, SOFC-X, Japan, 07-06-03. https://doi.org/10.1149/1.2729305

A neural network model in LaNixAl1-xO3 catalyst for methane reforming in SOFC. / Ciou, Sian Jie; Jhang, Ya Wun; Lai, Ying Jhih; Fung, Kuan-Zong; Hung, Min Hsiung; Chiang, Kai-Wei.

ECS Transactions - 10th International Symposium on Solid Oxide Fuel Cells, SOFC-X. 1 PART 2. ed. 2007. p. 1929-1937 (ECS Transactions; Vol. 7, No. 1 PART 2).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A neural network model in LaNixAl1-xO3 catalyst for methane reforming in SOFC

AU - Ciou, Sian Jie

AU - Jhang, Ya Wun

AU - Lai, Ying Jhih

AU - Fung, Kuan-Zong

AU - Hung, Min Hsiung

AU - Chiang, Kai-Wei

PY - 2007/12/1

Y1 - 2007/12/1

N2 - There has been a great interest in application of SOFC using hydrocarbon fuel, and the major issue associated with the improvement of steam reforming is the possibility to extend the area of operation conditions, and lead to low carbon formation. The improvement can be achieved by modifying the design of existing nickel catalysts. Generally, mathematical modeling can be considered as an important element in the methane reforming in terms of the avoidance of extensive experiments. In this article, a two layered feed-forward neural network has been trained with the back propagation algorithm to learn parameters in the process that the LaNixAl1-xO3(x = 0.1-0.9), reforms methane. The data used during the training procedure are generated by using of mass spectrometer after reforming. The average values of the errors for prediction are well below 5% The artificial neural network (ANN) model was capable of modeling the relationship between catalytic behaviors and the structure of catalytic well.

AB - There has been a great interest in application of SOFC using hydrocarbon fuel, and the major issue associated with the improvement of steam reforming is the possibility to extend the area of operation conditions, and lead to low carbon formation. The improvement can be achieved by modifying the design of existing nickel catalysts. Generally, mathematical modeling can be considered as an important element in the methane reforming in terms of the avoidance of extensive experiments. In this article, a two layered feed-forward neural network has been trained with the back propagation algorithm to learn parameters in the process that the LaNixAl1-xO3(x = 0.1-0.9), reforms methane. The data used during the training procedure are generated by using of mass spectrometer after reforming. The average values of the errors for prediction are well below 5% The artificial neural network (ANN) model was capable of modeling the relationship between catalytic behaviors and the structure of catalytic well.

UR - http://www.scopus.com/inward/record.url?scp=45249120811&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=45249120811&partnerID=8YFLogxK

U2 - 10.1149/1.2729305

DO - 10.1149/1.2729305

M3 - Conference contribution

AN - SCOPUS:45249120811

SN - 9781566775564

SN - 9781566775540

T3 - ECS Transactions

SP - 1929

EP - 1937

BT - ECS Transactions - 10th International Symposium on Solid Oxide Fuel Cells, SOFC-X

ER -

Ciou SJ, Jhang YW, Lai YJ, Fung K-Z, Hung MH, Chiang K-W. A neural network model in LaNixAl1-xO3 catalyst for methane reforming in SOFC. In ECS Transactions - 10th International Symposium on Solid Oxide Fuel Cells, SOFC-X. 1 PART 2 ed. 2007. p. 1929-1937. (ECS Transactions; 1 PART 2). https://doi.org/10.1149/1.2729305