journal article·2023-09

Time to market reduction for hydrogen fuel cell stacks using Generative Adversarial Networks

Nicolas Morizet, Perceval Desforges, Christophe Geissler, Elodie Pahon, Samir Jemei, Daniel Hissel

Publisher page

Abstract

To face the dependency on fossil fuels and limit carbon emissions, fuel cells are a very promising technology and appear to be a key candidate to tackle the increase of the energy demand and promote the energy transition. To meet future needs for both transport and stationary applications, the time to market of fuel cell stacks must be drastically reduced. Here, a new concept to shorten their development time by introducing a disruptive and highefficiency data augmentation approach based on artificial intelligence is presented. Our results allow reducing the testing time before introducing a product on the market from a thousand to a few hours. The innovative concept proposed here can support engineering and research tasks during the fuel cell development process to achieve decreased development costs alongside a reduced time to market.
Source: openaire · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Fuel Cells and Related Materials · Machine Learning in Materials Science · Energy Efficiency and Management

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (45)

Show source-provided references
1. IEA · 2021
2. Hydrogen production via microwave-induced water splitting at low temperature10.1038/s41560-020-00720-6 ↗
3. Thermo-electrochemical production of compressed hydrogen from methane with near-zero energy loss10.1038/s41560-017-0029-4 ↗
4. Economics of converting renewable power to hydrogen10.1038/s41560-019-0326-1 ↗
5. Hydrogen storage: Cold feat10.1038/nenergy.2016.167 ↗
6. Hydrogen storage: Pressure swing10.1038/nenergy.2017.122 ↗
7. Hydrogen storage: Improving reversibility10.1038/nenergy.2017.64 ↗
8. Hydrogen evolution: Guiding principles10.1038/nenergy.2016.155 ↗
9. Techno-economic and policy requirements for the market-entry of the fuel cell micro-CHP system in the residential sector10.1016/j.apenergy.2015.01.007 ↗
10. Experience curve development and cost reduction disaggregation for fuel cell markets in Japan and the US10.1016/j.apenergy.2017.01.056 ↗
11. Hydrogen on the rise10.1038/nenergy.2016.127 ↗
12. New roads and challenges for fuel cells in heavy-duty transportation10.1038/s41560-021-00775-z ↗
13. Flexible grid-based electrolysis hydrogen production for fuel cell vehicles reduces costs and greenhouse gas emissions10.1016/j.apenergy.2020.115651 ↗
14. Dynamic analysis of well-to-wheel electric and hydrogen vehicles greenhouse gas emissions: Focusing on consumer preferences and power mix changes in South Korea10.1016/j.apenergy.2019.114281 ↗
15. Moving forward with fuel cells10.1038/s41560-021-00846-1 ↗
16. Scenario analysis of lightweight and electric-drive vehicle market penetration in the long-term and impact on the light-duty vehicle fleet10.1016/j.apenergy.2017.05.054 ↗
17. Lightweight actor-critic generative adversarial networks for real-time smart generation control of microgrids10.1016/j.apenergy.2022.119163 ↗
18. Time series generative adversarial network controller for long-term smart generation control of microgrids10.1016/j.apenergy.2020.116069 ↗
19. A deep generative model for probabilistic energy forecasting in power systems: normalizing flows10.1016/j.apenergy.2021.117871 ↗
20. Data-driven scenario generation of renewable energy production based on controllable generative adversarial networks with interpretability10.1016/j.apenergy.2021.118387 ↗
21. Scenarios modelling for forecasting day-ahead electricity prices: Case studies in Australia10.1016/j.apenergy.2021.118296 ↗
22. Data augmentation for time series regression: Applying transformations, autoencoders and adversarial networks to electricity price forecasting10.1016/j.apenergy.2021.117695 ↗
23. A novel semi-supervised data-driven method for chiller fault diagnosis with unlabeled data10.1016/j.apenergy.2021.116459 ↗
24. Impedance-based capacity estimation for lithium-ion batteries using generative adversarial network10.1016/j.apenergy.2021.118317 ↗
25. 2022
26. J. Hunger, et al., Development of PEM Fuel Cell Stack Reference Test Procedures for Industry, FCH JU Grant Agreement 303445, 2015,.
27. Battelle Memorial Institute, Manufacturing cost analysis of 100 and 250kW fuel cell systems for primary power and combined heat and power applications, DOE Contract No. DE–EE0005250, 2017,.
28. 2021
29. Cathode starvation as an accelerated conditioning procedure for perfluorosulfonic acid ionomer fuel cells10.1016/j.powera.2020.100012 ↗
30. Goodfellow · 2014
31. Equilibrium points in n-person games10.1073/pnas.36.1.48 ↗
32. Gulrajani · 2017
33. Villani · 2003
34. Optimal mass transport: Signal processing and machine-learning applications10.1109/MSP.2017.2695801 ↗
35. Generating energy data for machine learning with recurrent generative adversarial networks10.3390/en13010130 ↗
36. Kingma · 2017
37. Pinetz · 2020
38. Salimans · 2016
39. Heusel · 2018
40. Shmelkov · 2018
41. Use of neural signals to evaluate the quality of generative adversarial network performance in facial image generation10.1007/s12559-019-09670-y ↗
42. Kendall’s tau
43. The significance probability of the smirnov two-sample test10.1007/BF02589501 ↗
44. LIII. On lines and planes of closest fit to systems of points in space10.1080/14786440109462720 ↗
45. A review on the proton-exchange membrane fuel cell break-in physical principles, activation procedures, and characterization methods10.1016/j.jpowsour.2023.233168 ↗