2 results
Search Results
Now showing 1 - 2 of 2
Article Citation - WoS: 3Citation - Scopus: 2Parametric Sensitivity Analysis and Performance Evaluation of High-Temperature Anion-Exchange Membrane Fuel Cell(Mdpi, 2022) Mehrtash, MehdiIn this paper, a three-dimensional model of a high-temperature anion-exchange membrane fuel cell (HT-AEMFC) operating at 110 degrees C is presented. All major transport phenomena along with the electrochemical reactions that occur in the cell are modeled. Since the water is exclusively in the form of steam and there is no phase transition to deal with in the cell, the water management is greatly simplified. The cell performance under various current loads is evaluated, and the results are validated against the experimental data. The cell performance is examined across a range of operating conditions, including cell temperature, inlet flow rate, and inlet relative humidity (RH). The critical link between the local distributions of species and local current densities along the channels is identified. The distribution of reactants continuously drops in the gas flow direction along the flow channels, causing a non-uniform local current distribution that becomes more pronounced at high current loads, where the rate of water generation increases. The findings show that while a higher inlet flow rate enhances the cell performance, a lower flow rate causes it to drop because of reactant depletion in the anode. The sensitivity analysis reveals that the performance of an AEMFC is highly dependent on the humidity of the gas entering the cell. While high inlet RH on the cathode side enhances the cell performance, high inlet RH on the anode side deteriorates it.Article Citation - WoS: 17Citation - Scopus: 23Regarding Solid Oxide Fuel Cells Simulation Through Artificial Intelligence: a Neural Networks Application(Mdpi, 2019) Baldinelli, Arianna; Barelli, Linda; Bidini, Gianni; Bonucci, Fabio; Iskenderoglu, Feride CansuBecause of their fuel flexibility, Solid Oxide Fuel Cells (SOFCs) are promising candidates to coach the energy transition. Yet, SOFC performance are markedly affected by fuel composition and operative parameters. In order to optimize SOFC operation and to provide a prompt regulation, reliable performance simulation tools are required. Given the high variability ascribed to the fuel in the wide range of SOFC applications and the high non-linearity of electrochemical systems, the implementation of artificial intelligence techniques, like Artificial Neural Networks (ANNs), is sound. In this paper, several network architectures based on a feedforward-backpropagation algorithm are proposed and trained on experimental data-set issued from tests on commercial NiYSZ/8YSZ/LSCF anode supported planar button cells. The best simulator obtained is a 3-hidden layer ANN (25/22/18 neurons per layer, hyperbolic tangent sigmoid as transfer function, obtained with a gradient descent with adaptive learning rate backpropagation). This shows high accuracy (RMS = 0.67% in the testing phase) and successful application in the forecast of SOFC polarization behaviour in two additional experiments (RMS in the order of 3% is scored, yet it is reduced to about 2% if only the typical operating current density range of real application is considered, from 300 to 500 mA.cm(-2)). Therefore, the neural tool is suitable for system simulation codes/software whether SOFC operating parameters agree with the input ranges (anode feeding composition 0-48%(vol) H-2, 0-38%(vol) CO, 0-45%(vol) CH4, 9-32%(vol) CO2, 0-54%(vol) N-2, specific equivalent hydrogen flow-rate per unit cell active area 10.8-23.6 mL.min(-1).cm(-2), current density 0-1300 mA.cm(-2) and temperature 700-800 degrees C).
