Performance prediction and analysis of a dead-end PEMFC stack using data-driven dynamic model

Mohammad Mahdi Barzegari, Seyed Majid Rahgoshay, Lliya Mohammadpour and Davood Toghraie

Energy, 2019, vol. 188, issue C

Abstract: In this paper, we derive a data-driven dynamic model of a dead-end cascade-type proton exchange membrane (PEM) fuel cell. We employ an Artificial neural network (ANN) method to build the nonlinear black-box model of the PEM fuel cell stack. Both anode and cathode sides of the stack are composed of two stages which the second stages of them operate in a dead-end condition. Identification experiments are accomplished for a 400 W PEM fuel cell stack consisting of 4 cells with a 225 cm2 membrane. The empirical model inputs are time, stack current, inlet reactant gases pressures and purge interval time, and the model output is stack voltage. The ANN is trained with a set of experimental data, and the trained model is then tested and validated with an independent set of data. The results reveal good agreement between the proposed black-box model and experimental data with adequate certainty. The proposed methodology can be applied to guide the controller design and fault diagnosis of the PEM fuel cell in the near future.

Keywords: PEM fuel cell; Artificial neural network; Dead-end; Data-driven model; Performance prediction (search for similar items in EconPapers)
Date: 2019
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (9)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S036054421931744X
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:188:y:2019:i:c:s036054421931744x

DOI: 10.1016/j.energy.2019.116049

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().