Gas composition modeling in a reformed Methanol Fuel Cell system using adaptive Neuro-Fuzzy Inference Systems

• Published in: International journal of hydrogen energy Vol. 38; no. 25; pp. 10577 - 10584
• Main Authors: Justesen, Kristian Kjær, Andreasen, Søren Juhl, Shaker, Hamid Reza, Ehmsen, Mikkel Præstholm, Andersen, John
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ltd 21.08.2013; Elsevier
• Subjects: Alternative fuels. Production and utilization; ANFIS; Applied sciences; Carbon dioxide; Energy; Exact sciences and technology; Fuels; Fuzzy-logic and neural networks; Gas composition modeling; HTPEM fuel cell; Hydrogen; Methanol; Reformed Methanol Fuel Cell; Fuzzy-logic and neural networks; Reformed Methanol Fuel Cell; ANFIS; Gas composition modeling; HTPEM fuel cell; Methanol; Fuzzy logic; Hydrogen; Neural network; Modeling; Fuel cell
• ISSN: 0360-3199; 1879-3487
• DOI: 10.1016/j.ijhydene.2013.06.013

This work presents a method for modeling the gas composition in a Reformed Methanol Fuel Cell system. The method is based on Adaptive Neuro-Fuzzy-Inference-Systems which are trained on experimental data. The developed models are of the H2, CO2, CO and CH3OH mass flows of the reformed gas. The ANFIS models are able to predict the mass flows with mean absolute errors for the H2 and CO2 models of less than 1% and 6.37% for the CO model and 4.56% for the CH3OH model. The models have a wide range of applications such as dynamic modeling, stoichiometry observation and control, advanced control algorithms, or fuel cell diagnostics systems. •Measurement of gas composition performed on an experimental setup.•Presents ANFIS models of the mass flow of H2, CO2, CO and CH3OH in the reformed gas.•The mean absolute errors for the H2 and CO2 models of less than 1%.•The mean absolute error of 6.37% for the CO model and 4.56% for the CH3OH model.•Usefulness for stoichiometry analysis in RMFC system demonstrated.