Articles & Issues

Conflict of Interest: In relation to this article, we declare that there is no conflict of interest.

This is an Open-Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/bync/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

All issues

오류역전파 신경망 이론을 이용한 인산형 연료전지 공정의 전산모사

A simulation Study of Phosphoric Acid Fuel Cell Process Using Error Back-propagation Neural Network

이원재 김성준 설용건 이태희

Lee WJ Kim SJ Shul YG Lee TH

HWAHAK KONGHAK, October 1995, 33(5), 610-620(11), NONE

Download PDF

Abstract

오류역전파 신경망을 인산형 연료전지의 조업변수인 산소 및 수소 유량, 작동온도에 대하여 학습시켜 연료전지 성능예측모델을 구성하였다. 또한 구성된 모델로 다양한 조업조건에서의 단위전지 성능을 예측하여 이를 실험과 비교하였으며, 학습된 신경망을 상용 공정모사기인 ASPEN PLUS의 단위공정으로 도입하여 50kW 출력의 연료전지 공정을 구성한 후 조업변수에 대한 영향을 살펴보았다. 3개의 층으로 구성된 오류역전파 신경망은 학습단계상수와 모멘텀이 각각 0.7 및0.9 인 경우 단위 전지의 성능곡선을 가장 정확히 학습하였으며, 신경망모델은 수소 및 산송의 유량, 온도의 변화에 따른 단위전지 성능곡선의 변화를 정확히 예측하였다. 연료전지 전체공정의 모사 결과, 개질기의 경우 600℃, 상압에서 수증기/탄화수소 비율이 2.6일 때 최대 출력을 나타내었으며, 연료전지 본체의 작동온도를 190℃ 정도로 하는 것이 적절함을 알 수 있다.

A performance modeling of phosphoric acid fuel cell was constructed using error back-propagetion neural network with generalized delta rule. The network was trained to produce the performance curve according to cell temperatures, H₂ flow rates and O₂ flow rates. The reliability of performance prediction was verified by comparing the experimental data of unit cell. The three layered error back-propagation net-work learned exactly the performance curve of unit cell when the step size coefficient was 0.7 and the momentum was 0.9. It offered reasonable prediction for various O₂ and H₂ flow rates and temperatures. This neural network combined to commercial process simulator ASPEN PLUS as a unit for fuel cell stack. In this process simulation, 50kW PAFC system was selected, and the effects of operating variables on the performance of the system were also investigated. The maximum power of fuel cell was achieved when the reformer temperature was 600℃ at 1 atm, and steam-carbon ratio was 2.6. It is proper to maintain the operating temperature of fuel cell at 190℃.

Keywords

References

Bockris JOM, Srinivasan S, "Fuel Cells: Their Electrochemistry," McGraw-Hill Inc., NY (1969)
Berger C, "Handbook of Fuel Cell Technology," Prectice-Hall Inc., NJ (1968)
McDougall S, "Fuel Cells," John Wiley & Sons, NY (1976)
서정원, 김성준, 설용건, 이태희, 에너지공학, 2(1), 75 (1993)
Wasserman PD, "Neural Computing (Theory and Practice)," Van Nostrand Reinhold, NY (1989)
Khanna T, "Foundations of Neural Networks," Addison-Wesley, NY (1990)
Caudill M, Butler C, "Understanding Neural Network (Computer Explorations), MIT Press (1992)
Cho SB, Kim JH, "International Joint Conference Neural Networks," San Diego, Vol. I, 345 (1990)
Kamimura R, "International Joint Conference Neural Networks," San Diego, Vol. I, 201 (1990)
송정준, 박사학위논문, 한국과학기술원, 대전 (1993)
Ungar LH, Powell BA, Kamens SN, Comput. Chem. Eng., 14, 561 (1990)
Bhat N, McAvoy TJ, Comput. Chem. Eng., 14, 573 (1990)
Ydstie BE, Comput. Chem. Eng., 14, 583 (1990)
Psichogios DC, Ungar LH, Ind. Eng. Chem. Res., 30, 2564 (1991)
Widrow B, Stearns S, "Adaptive Signal Processing," Prentice-Hall, Englewood Liffs, NJ (1985)
Leonard JA, Kramer MA, Comput. Chem. Eng., 14, 337 (1990)
Rumelhart DE, Hilton GE, Williams RJ, "Parallel Distributed Processing," Cambridge, MA (1986)
노용우, 박사학위논문, 연세대학교, 서울 (1991)
Jalan VM, Bushnell CL, U.S. Patent, 4,136,059
이승훈, 석사학위논문, 연세대학교, 서울 (1991)
서동우, 석사학위논문, 연세대학교, 서울 (1993)