.png){kind=icon}
.png){kind=icon}
Return
Molten carbonate electrolysis modeling and optimization using feedforward neural networks
.png){kind=icon}
OA
AI
A
J
A
P
C
K
O
Ł
K
J
DOI：10.1016/j.energy.2026.142125.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Develops MCE-specific compact ANN surrogates for thermal and gas-flow effects. • Harmonizes literature data using area-normalized operating variables. • Evaluates four MCE scenarios: temperature, fuel, oxidant, and thermal-flow. • Reports separate training, validation, and unseen test-set ANN errors. • Uses the unified ANN surrogate for constrained operating-point optimization.
Keywords:
Artificial neural networks
Molten carbonate electrolysis
Mathematical modeling
Machine learning
Electrolysis
Journal
IF:
9.4
Papers:
4.2W
Citations:
20.2W
Organization
Cited Papers