Efficiency optimization of fuel cell systems with energy recovery: An integrated approach based on modeling, machine learning, and genetic algorithm
Source abstract
Abstract
Maximizing the efficiency of fuel cell systems (FCS) with energy recovery capabilities is crucial for advancing high-efficiency FCS technology. This research aims to explore the maximization of FCS efficiency through the optimization of operational parameters and to elucidate the synergistic effects between parameter optimization and energy recovery. Employing an integrated approach that combines model simulation, experiments, machine learning, and genetic algorithm (GA), this work addresses key technical challenges in developing an efficient FCS model and a high-precision surrogate model. It also tackles the critical problem of achieving maximum system efficiency through the optimization of operational parameters and energy recovery. The findings indicate that the data-injection-based model simplifies the computational process and effectively validated over long time scales. Feature selection and network quality assessment ensure the precision and reliability of the long short-term memory (LSTM) network. Optimization using GA in conjunction with the LSTM surrogate model enables a rapid and accurate determination of the system`s maximum net output power and corresponding operational conditions. The results demonstrate a 6 % increase in the system`s net output power, with the system efficiency consistently surpassing 55 %. Moreover, energy recovery consistently boosts optimized system efficiency by about 1.6–1.7 %.
Source: expertdata · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Fuel Cells and Related Materials · Electrocatalysts for Energy Conversion · Advancements in Solid Oxide Fuel Cells
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (46)
Show source-provided references
1. Wu · Electrochem. Energy Rev. · 2020 · 3 · 46610.1007/s41918-020-00068-1 ↗
2. Cullen · Nat. Energy · 2021 · 6 · 46210.1038/s41560-021-00775-z ↗
3. Jiao · Nature · 2021 · 595 · 36110.1038/s41586-021-03482-7 ↗
4. Pu · Energy and AI · 2024 · 1610.1016/j.egyai.2024.100353 ↗
5. Tongsh · Joule · 2024 · 8 · 17510.1016/j.joule.2023.12.003 ↗
6. Ahsan · Energy Rep. · 2021 · 7 · 263510.1016/j.egyr.2021.05.007 ↗
7. Chen · Appl. Therm. Eng. · 2023 · 233
8. Zhang · Appl. Therm. Eng. · 2020 · 180
9. Gong · Appl. Energy · 2022 · 32510.1016/j.apenergy.2022.119839 ↗
10. Tan · Int. J. Hydrogen Energy · 2022 · 47 · 3579010.1016/j.ijhydene.2022.08.154 ↗
11. Ge · Int. J. Hydrogen Energy · 2024 · 57 · 13610.1016/j.ijhydene.2023.12.294 ↗
12. Xu · Fuel · 2024 · 363
13. Wang · J. Power Sources · 2019 · 434
14. Yang · Appl. Energy · 2019 · 256
15. Peng · Energy Convers. Manag. · 2020 · 20510.1016/j.enconman.2019.112385 ↗
16. Yan · Int. J. Heat Mass Tran. · 2020 · 15210.1016/j.ijheatmasstransfer.2020.119538 ↗
17. Yuan · J. Power Sources · 2020 · 46810.1016/j.jpowsour.2020.228376 ↗
18. Chen · Int. J. Hydrogen Energy · 2023 · 48 · 107510.1016/j.ijhydene.2022.09.298 ↗
19. Wei · Chem. Eng. J. · 2023 · 471
20. Zhou · Int. J. Hydrogen Energy · 2023 · 48 · 2071710.1016/j.ijhydene.2023.03.017 ↗
21. Zhou · Appl. Energy · 2023 · 34310.1016/j.apenergy.2023.121226 ↗
22. Zhou · Fuel · 2024 · 357
23. Niu · J. Electrochem. Soc. · 2018 · 165 · F61310.1149/2.0261809jes ↗
24. Wang · Energy and AI · 2020 · 1
25. Wu · Appl. Energy · 2021 · 303
26. Mütter · Energy Convers. Manag. · 2023 · 29110.1016/j.enconman.2023.117263 ↗
27. Legala · Energy and AI · 2022 · 10
28. Su · Int. J. Hydrogen Energy · 2022 · 47 · 2903710.1016/j.ijhydene.2022.06.240 ↗
29. Kheirandish · Int. J. Hydrogen Energy · 2016 · 41 · 958510.1016/j.ijhydene.2016.02.046 ↗
30. Wilberforce · Energy Rep. · 2022 · 8 · 1284310.1016/j.egyr.2022.09.104 ↗
31. Tian · Appl. Energy · 2021 · 28810.1016/j.apenergy.2021.116632 ↗
32. Ding · Energy and AI · 2022 · 910.1016/j.egyai.2022.100170 ↗
33. Yuan · Nano Energy · 2024 · 122
34. Han · Energy Convers. Manag. · 2016 · 113 · 5210.1016/j.enconman.2016.01.045 ↗
35. Li · Energy Convers. Manag. · 2021 · 236
36. Li · Fuel · 2024 · 358
37. Lu · Appl. Energy · 2024 · 35510.1016/j.apenergy.2023.122255 ↗
38. Feng · Appl. Energy · 2022 · 31710.1016/j.apenergy.2022.119158 ↗
39. Xu · Energy Convers. Manag. · 2022 · 26810.1016/j.enconman.2022.116026 ↗
40. Lan · Int. J. Hydrogen Energy · 2020 · 45 · 1250110.1016/j.ijhydene.2020.02.150 ↗
41. Ding · Int. J. Hydrogen Energy · 2024 · 58 · 151410.1016/j.ijhydene.2024.01.309 ↗
42. Bao · Energy · 2023 · 28410.1016/j.energy.2023.129267 ↗
43. Wang · Energy and AI · 2023 · 14
44. Pukrushpan · 2003
45. Jiao · Prog Energ Combust · 2011 · 37 · 22110.1016/j.pecs.2010.06.002 ↗
46. Li · Chinese Journal of Engineering · 2022 · 44 · 1090