.png){kind=icon}
.png){kind=icon}
Return
Domain-enforced and operator-in-the-loop neural simulation platform for techno-enviro-economic performance enhancement of gas turbine system
.png){kind=icon}
PRE
AI
W
A
A
G
M
V
DOI：10.1016/j.compchemeng.2025.109529.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Operator-in-the-loop, uncertainty-aware AI for a 395-MW gas turbine • Mahalanobis constraints enforce trustworthy, domain-consistent set-points • KAN surrogate achieves R2≥0.96, outperforming ANN and DINN on tests. • Platform cuts CO2 by 2.9 kton/yr and saves $0.95M/yr operating cost • Open-source interface with failure-mode guidance for safe deployment.
Journal
C
IF:
3.9
Papers:
8.1K
Citations:
1.7W
Organization
Cited Papers