Title: Dynamic modelling of PEMFC by adaptive neuro-fuzzy inference system

Authors: Milad Karimi; Alireza Rezazadeh

Addresses: Department of Electrical and Computer Engineering, Shahid Beheshti University, G.C., Evin, Tehran 198396311, Iran ' Department of Electrical and Computer Engineering, Shahid Beheshti University, G.C., Evin, Tehran 198396311, Iran

Abstract: One of the most important issues in control subject of proton exchange membrane fuel cell (PEMFC) is finding lots of undetermined, nonlinear and dependent variables of PEMFC. It is necessary to develop a fast and reliable model to control the complex dynamic behaviour of PEMFC. In this paper, adaptive neuro-fuzzy inference system (ANFIS) is used to model the dynamic voltage of PEMFC stack. The ANFIS is trained with a set of experimental data which are taken from a 5 kW PEMFC setup plant. The artificial neural network (ANN) is selected to be compared with the ANFIS in terms of speed and accuracy. The results show that there is a good agreement between ANFIS output and real plant as well as the physical model, so the model can be used to predict dynamic behaviour of the system.

Keywords: ANFIS; adaptive neuro-fuzzy inference system; dynamic modelling; fuzzy logic; artificial neural networks; ANNs; PEMFC; proton exchange membrane fuel cells; dynamic voltage.

DOI: 10.1504/IJEHV.2016.080726

International Journal of Electric and Hybrid Vehicles, 2016 Vol.8 No.4, pp.289 - 301

Received: 12 Jul 2016
Accepted: 17 Jul 2016

Published online: 02 Dec 2016 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article