An actor–critic algorithm to maximize the power delivered from direct methanol fuel cells

Hongbin Xu, Yang Jeong Park, Zhichu Ren, Daniel J. Zheng, Davide Menga, Haojun Jia, Chenru Duan, Guanzhou Zhu, Yuriy Román-Leshkov, Yang Shao-Horn () and Ju Li ()
Additional contact information
Hongbin Xu: Massachusetts Institute of Technology
Yang Jeong Park: Massachusetts Institute of Technology
Zhichu Ren: Massachusetts Institute of Technology
Daniel J. Zheng: Massachusetts Institute of Technology
Davide Menga: Massachusetts Institute of Technology
Haojun Jia: Massachusetts Institute of Technology
Chenru Duan: Massachusetts Institute of Technology
Guanzhou Zhu: Massachusetts Institute of Technology
Yuriy Román-Leshkov: Massachusetts Institute of Technology
Yang Shao-Horn: Massachusetts Institute of Technology
Ju Li: Massachusetts Institute of Technology

Nature Energy, 2025, vol. 10, issue 8, 951-961

Abstract: Abstract Optimizing nonlinear time-dependent control in complex energy systems such as direct methanol fuel cells (DMFCs) is a crucial engineering challenge. The long-term power delivery of DMFCs deteriorates as the electrocatalytic surfaces become fouled. Dynamic voltage adjustment can clean the surface and recover the activity of catalysts; however, manually identifying optimal control strategies considering multiple mechanisms is challenging. Here we demonstrated a nonlinear policy model (Alpha-Fuel-Cell) inspired by actor–critic reinforcement learning, which learns directly from real-world current–time trajectories to infer the state of catalysts during operation and generates a suitable action for the next timestep automatically. Moreover, the model can provide protocols to achieve the required power while significantly slowing the degradation of catalysts. Benefiting from this model, the time-averaged power delivered is 153% compared to constant potential operation for DMFCs over 12 hours. Our framework may be generalized to other energy device applications requiring long-time-horizon decision-making in the real world.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41560-025-01804-x Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natene:v:10:y:2025:i:8:d:10.1038_s41560-025-01804-x

Ordering information: This journal article can be ordered from
https://www.nature.com/nenergy/

DOI: 10.1038/s41560-025-01804-x

Access Statistics for this article

Nature Energy is currently edited by Fouad Khan

More articles in Nature Energy from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().