| 학회 |
한국화학공학회 |
| 학술대회 |
2005년 봄 (04/22 ~ 04/23, 여수대학교) |
| 권호 |
11권 1호, p.511 |
| 발표분야 |
에너지/환경 |
| 제목 |
Development of Reduced Order Models (ROM) for Timely Prediction of the Behavior of Proton Exchange Membrane Fuel Cells |
| 초록 |
In this paper, we discuss the development of reduced-order, neural network (NN) models for quickly predicting the flow of reactants in a proton exchange membrane fuel cell manifold. A feed-forward, back-propagation neural network is used in this work. The data for NN training are generated from detailed CFD simulations of the manifold using Fluent. The input parameters to the NN are: channel dimension, mass flow rate, inlet gas temperature and pressure. The output values are: H2 consumption, pressure drop and mean velocity in the channels. The ability of the proposed network to predict detailed flow behaviors in the manifold is discussed. |
| 저자 |
신동일1, 오태훈1, R. Rengasamy2
|
| 소속 |
1명지대, 2Clarkson Univ. |
| 키워드 |
Fuel cell; modeling and simulation; reduced order model
|
| E-Mail |
|
| 원문파일 |
초록 보기 |
