Abstract
Solid oxide fuel cells are becoming increasingly important in various applications, from households to large-scale power plants. However, these electrochemical energy conversion devices have complex behavior that is difficult to understand and optimize. A numerical simulation is a primary tool for analysis and optimization-design. One of the most significant challenges in this field is improving microscale transport phenomena and electrode reaction models. Two main categories of simulation are black-box and white-box models. The former requires large experimental datasets and lacks physical constraints, while the latter inherits the inaccuracy of typical electrochemical reaction models. Here we show a micro-scale artificial neural network-supported numerical simulation that allows for overcoming those issues. In our research, we substituted one equation in the system, an electrochemical model, with an artificial neural network prediction. The data-driven prediction is constrained and must satisfy all reminded balance equations in the system. The results show that the proposed model can simulate an anode-electrode’s thermodynamic losses with improved accuracy compared with the classical approach. The coefficient of determination R2 for the proposed model was equal to 0.8810 for 800 °C, 0.8720 for 900 °C, and 0.8436 for 1000 °C. The findings open a way for improving the accuracy and computational complexity of electrochemical models in solid oxide fuel cell simulations.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.