Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

CHEMNODE: CHEMICAL KINETICS SOLVER APPROACH BASED ON NEURAL ORDINARY DIFFERENTIAL EQUATIONS

Software ·
OSTI ID:1787853
This software contains an algorithm to model and predict the time evolution of chemical kinetics in reacting flow simulations using neural ordinary differential equations (NODEs). The approach works by using artificial neural networks to predict the chemical source terms. It achieves this by using forward-mode automatic differentiation and the Levenberg-Marquardt algorithm to adjust the neural network parameters, such that the discrepancies between the actual and predicted species profiles are minimized.
Short Name / Acronym:
CHEMNODE; 006029MLTPL00
Version:
00
Programming Language(s):
Medium: X; OS: All
Research Organization:
Argonne National Laboratory (ANL), Argonne, IL (United States)
Sponsoring Organization:
USDOE Office of Environmental Management (EM), Regulatory and Policy Affairs. Waste and Materials Management
Contributing Organization:
ARGONNE NATIONAL LABORATORY
DOE Contract Number:
AC02-06CH11357
OSTI ID:
1787853
Country of Origin:
United States

Similar Records

Ordinary Differential Equation System Solver
Software · Wed Mar 04 19:00:00 EST 1992 · OSTI ID:code-12039

Modular Expression Language for Ordinary Differential Equation Editing
Software · Thu Jan 19 00:00:00 EST 2017 · OSTI ID:1343917

Modeling Time Series Data with Ordinary Differential Equations and Neural Networks
Software · Thu Aug 08 20:00:00 EDT 2019 · OSTI ID:code-31120

Related Subjects