Embedding trained neural networks as surrogates in a mixed-integer quadratically constrained program enables simultaneous optimization of discrete process selection and continuous parameters for Fischer-Tropsch kerosene, identifying hybrid ATR-biomass routes as lowest-cost at zero net emissions.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CE 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Superstructure Optimization with Embedded Neural Networks for Sustainable Aviation Fuel Production
Embedding trained neural networks as surrogates in a mixed-integer quadratically constrained program enables simultaneous optimization of discrete process selection and continuous parameters for Fischer-Tropsch kerosene, identifying hybrid ATR-biomass routes as lowest-cost at zero net emissions.