In this work, Artificial Neural Network (ANN) is applied to model the electrical behavior of Solid oxide electrolyzer cells (SOEC). Experimental data from different available sources are utilized for making the model. The error-backpropagation algorithm is used to train the ANN model. Different parameters of cell working conditions and architecture of SOEC are investigated as inputs to the ANN model. The parameters of the cell working conditions are cell temperature, current density, and cathode flow rates. The parameters of the cell architecture are the cathode thickness, electrolyte thickness, and the anode thickness. The model predicts the voltage of the cell. The ANN that models SOEC is presented and discussed. The results demonstrate that ANN can successfully learn the internal relationships of the available experimental data and model the SOEC with a high accuracy and generalizability. Copyright (C) 2015, Hydrogen Energy Publications, LLC. Published by Elsevier Ltd. All rights reserved.