An artificial neural network (ANN) and a genetic algorithm (GA) are employed to model and optimize cell parameters to improve the performance of singular, intermediate‐temperature, solid oxide fuel cells (IT‐SOFCs). The ANN model uses a feed‐forward neural network with an error back‐propagation algorithm. The ANN is trained using experimental data as a black‐box without using physical models. The developed model is able to predict the performance of the SOFC. An optimization algorithm is utilized to select the optimal SOFC parameters. The optimal values of four cell parameters (anode support thickness, anode support porosity, electrolyte thickness, and functional layer cathode thickness) are determined by using the GA under different conditions. The results show that these optimum cell parameters deliver the highest maximum power density under different constraints on the anode support thickness, porosity, and electrolyte thickness.
Achieving high performance from a solid oxide fuel cell (SOFC) requires optimal design based on parametric analysis. In this paper, design parameters, including anode support porosity, thicknesses of electrolyte, anode support, and cathode functional layers of a single, intermediate temperature, anode‐supported planar SOFC, are analyzed. The response surface methodology (RSM) technique based on an artificial neural network (ANN) model is used. The effects of the cell parameters on its performance are calculated to determine the significant design factors and interaction effects. The obtained optimum parameters are adopted to manufacture the single units of an SOFC through tape casting and screen‐printing processes. The cell is tested and its electrochemical characteristics, which show a satisfactory performance, are discussed. The measured maximum power density (MPD) of the fabricated SOFC displays a promising performance of 1.39 W cm–2. The manufacturing process planned to fabricate the SOFC can be used for industrial production purposes.
In the manufacturing process of solid oxide fuel cells (SOFCs), the residual stresses and curvature are developed in components due to the differences in material properties of cell layers. Residual stress may lead to the crack formation in the cell layers and facilitates cell fracture. In this work, the changes of the residual stress in the electrolyte layer of the anode-supported planar solid oxide fuel cells are experimentally determined at room temperature. The “sin2ψ” technique of X-ray diffraction method is employed to measure the residual stress in the half-cell samples. Investigation on the changes of the residual stress and curvature state in the scaling-up process of the cell is crucial for commercial use. Therefore, several cells with different sizes and shapes are investigated to evaluate the potential impact of cell size and cell shape on the residual thermal stress. Values of about −610 MPa are determined for the electrolyte layer on an oxidized ∼400 μm thick anode substrate. The results reveal that despite the effect of size and shape on the radius of curvature, these parameters have no significant impact on the residual stress level.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.