Kinetics-constrained neural ordinary differential equations: Artificial neural network models tailored for small data to boost kinetic model development
Authors:
- Aleksandr FedorovAFAleksandr Fedorov
- Anna PerechodjukAPAnna Perechodjuk
- David LinkeDLDavid Linke
- 25 October 2023
- journal article
- research article
- Published by Elsevier in Chemical Engineering Journal
- Vol. 477
Abstract
No abstract availableKeywords
All Related Versions
Funding Information
- Deutsche Forschungsgemeinschaft
- Bundesministerium für Forschung, Technologie und Raumfahrt
This publication has 50 references indexed in Scilit:
- Kinetics and mechanism of partial oxidation of ethane to ethylene and acetic acid over MoV type catalystsApplied Catalysis A: General, 2010
- Fischer–Tropsch on Iron with H2/CO and H2/CO2 as Synthesis Gases: The Episodes of Formation of the Fischer–Tropsch Regime and Construction of the CatalystTopics in Catalysis, 2003
- Kinetics of CO2 Hydrogenation on a K-Promoted Fe CatalystIndustrial & Engineering Chemistry Research, 2001
- Kinetics and Selectivity of the Fischer–Tropsch Synthesis: A Literature ReviewCatalysis Reviews, 1999
- The molecular weight distribution of the products of the Fischer-Tropsch synthesisRussian Chemical Reviews, 1994
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989
- Automatic Selection of Methods for Solving Stiff and Nonstiff Systems of Ordinary Differential EquationsSIAM Journal on Scientific and Statistical Computing, 1983
- The Fischer‐Tropsch Synthesis: Molecular Weight Distribution of Primary Products and Reaction MechanismAngewandte Chemie International Edition, 1976
- Diagnostic criteria for heat transport limitations in fixed bed reactorsJournal of Catalysis, 1971
- Molecular Size Distribution in Linear Condensation Polymers1Journal of the American Chemical Society, 1936