Leveraging Neural Networks and Genetic Algorithms to Refine Electrode Properties in Redox Flow Batteries
<jats:p>Redox flow batteries are a nascent, yet promising, energy storage technology for which widespread deployment is hampered by technical and economic challenges. A performance-determining component in the reactor, present-day electrodes are often borrowed from adjacent electrochemical tec...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
The Electrochemical Society
2022
|
| Online Access: | https://hdl.handle.net/1721.1/142493 |
| _version_ | 1811083779458990080 |
|---|---|
| author | Tenny, Kevin M Braatz, Richard D Chiang, Yet-Ming Brushett, Fikile R |
| author2 | Massachusetts Institute of Technology. Department of Chemical Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Chemical Engineering Tenny, Kevin M Braatz, Richard D Chiang, Yet-Ming Brushett, Fikile R |
| author_sort | Tenny, Kevin M |
| collection | MIT |
| description | <jats:p>Redox flow batteries are a nascent, yet promising, energy storage technology for which widespread deployment is hampered by technical and economic challenges. A performance-determining component in the reactor, present-day electrodes are often borrowed from adjacent electrochemical technologies rather than specifically designed for use in flow batteries. A lack of structural diversity in commercial offerings, coupled with the time constraints of wet-lab experiments, render broad electrode screening infeasible without a modeling complement. Herein, an experimentally validated model of a vanadium redox flow cell is used to generate polarization data for electrodes with different macrohomogeneous properties (thickness, porosity, volumetric surface area, and kinetic rate constant). Using these data sets, we then build and train a neural network with minimal average root-mean squared testing error (17.9 ± 1.8 mA cm<jats:sup>−2</jats:sup>) to compute individual parameter sweeps along the cell polarization curve. Finally, we employ a genetic algorithm with the neural network to identify electrode property values for improving cell power density. While the developed framework does not supplant experimentation, it is generalizable to different redox chemistries and may inform future electrode design strategies.</jats:p> |
| first_indexed | 2024-09-23T12:38:58Z |
| format | Article |
| id | mit-1721.1/142493 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T12:38:58Z |
| publishDate | 2022 |
| publisher | The Electrochemical Society |
| record_format | dspace |
| spelling | mit-1721.1/1424932023-01-27T18:20:09Z Leveraging Neural Networks and Genetic Algorithms to Refine Electrode Properties in Redox Flow Batteries Tenny, Kevin M Braatz, Richard D Chiang, Yet-Ming Brushett, Fikile R Massachusetts Institute of Technology. Department of Chemical Engineering Massachusetts Institute of Technology. Department of Materials Science and Engineering <jats:p>Redox flow batteries are a nascent, yet promising, energy storage technology for which widespread deployment is hampered by technical and economic challenges. A performance-determining component in the reactor, present-day electrodes are often borrowed from adjacent electrochemical technologies rather than specifically designed for use in flow batteries. A lack of structural diversity in commercial offerings, coupled with the time constraints of wet-lab experiments, render broad electrode screening infeasible without a modeling complement. Herein, an experimentally validated model of a vanadium redox flow cell is used to generate polarization data for electrodes with different macrohomogeneous properties (thickness, porosity, volumetric surface area, and kinetic rate constant). Using these data sets, we then build and train a neural network with minimal average root-mean squared testing error (17.9 ± 1.8 mA cm<jats:sup>−2</jats:sup>) to compute individual parameter sweeps along the cell polarization curve. Finally, we employ a genetic algorithm with the neural network to identify electrode property values for improving cell power density. While the developed framework does not supplant experimentation, it is generalizable to different redox chemistries and may inform future electrode design strategies.</jats:p> 2022-05-11T18:27:03Z 2022-05-11T18:27:03Z 2021 2022-05-11T18:19:59Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/142493 Tenny, Kevin M, Braatz, Richard D, Chiang, Yet-Ming and Brushett, Fikile R. 2021. "Leveraging Neural Networks and Genetic Algorithms to Refine Electrode Properties in Redox Flow Batteries." Journal of The Electrochemical Society, 168 (5). en 10.1149/1945-7111/ABF77C Journal of The Electrochemical Society Attribution-NonCommercial-ShareAlike 4.0 International https://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf The Electrochemical Society ChemRxiv |
| spellingShingle | Tenny, Kevin M Braatz, Richard D Chiang, Yet-Ming Brushett, Fikile R Leveraging Neural Networks and Genetic Algorithms to Refine Electrode Properties in Redox Flow Batteries |
| title | Leveraging Neural Networks and Genetic Algorithms to Refine Electrode Properties in Redox Flow Batteries |
| title_full | Leveraging Neural Networks and Genetic Algorithms to Refine Electrode Properties in Redox Flow Batteries |
| title_fullStr | Leveraging Neural Networks and Genetic Algorithms to Refine Electrode Properties in Redox Flow Batteries |
| title_full_unstemmed | Leveraging Neural Networks and Genetic Algorithms to Refine Electrode Properties in Redox Flow Batteries |
| title_short | Leveraging Neural Networks and Genetic Algorithms to Refine Electrode Properties in Redox Flow Batteries |
| title_sort | leveraging neural networks and genetic algorithms to refine electrode properties in redox flow batteries |
| url | https://hdl.handle.net/1721.1/142493 |
| work_keys_str_mv | AT tennykevinm leveragingneuralnetworksandgeneticalgorithmstorefineelectrodepropertiesinredoxflowbatteries AT braatzrichardd leveragingneuralnetworksandgeneticalgorithmstorefineelectrodepropertiesinredoxflowbatteries AT chiangyetming leveragingneuralnetworksandgeneticalgorithmstorefineelectrodepropertiesinredoxflowbatteries AT brushettfikiler leveragingneuralnetworksandgeneticalgorithmstorefineelectrodepropertiesinredoxflowbatteries |