Stiffness-reduced neural ode models for data-driven reduced-order modeling of combustion chemical kinetics

Henry E. Dikeman, Hongyuan Zhang, Suo Yang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A novel methodology for data-driven reduced-order modeling of stiff ODE systems was developed. A combination of a reversible nonlinear mapping to a reduced-order space and a data-driven neural ordinary differential equation (ODE) model allows efficient training and inference upon complex and highly stiff systems (e.g., combustion chemical kinetics). By regularizing the reduced-order mapping with an estimate of local stiffness, the nonlinear autoencoder neural network model is optimized to learn the highest reconstruction accuracy stiffness-reduced compression of the full-order system. This combination of stiffness-reduced autoencoder and neural ODE models constitutes the proposed reduced-order neural ODE (RONODE) methodology. This method was then applied to both a plug flow reactor (PFR) and a continuous stirred tank reactor (CSTR) with a 53 species and 325 reaction propane-air combustion chemical mechanism (GRI 3.0 mechanism). The RONODE model attained a 1.9 × 10−4 root-mean-square (RMS) error with a computational speed-up factor of 3.1 on the PFR system, while on the less stiff CSTR system the method attained a 2.1 × 10−4 RMS error with a computational speed-up factor of 1.3.

Original languageEnglish (US)
Title of host publicationAIAA SciTech Forum 2022
PublisherAmerican Institute of Aeronautics and Astronautics Inc, AIAA
ISBN (Print)9781624106316
DOIs
StatePublished - 2022
EventAIAA Science and Technology Forum and Exposition, AIAA SciTech Forum 2022 - San Diego, United States
Duration: Jan 3 2022Jan 7 2022

Publication series

NameAIAA Science and Technology Forum and Exposition, AIAA SciTech Forum 2022

Conference

ConferenceAIAA Science and Technology Forum and Exposition, AIAA SciTech Forum 2022
Country/TerritoryUnited States
CitySan Diego
Period1/3/221/7/22

Bibliographical note

Funding Information:
S. Yang gratefully acknowledges the faculty start-up funding from the University of Minnesota (UMN). H.E. Dikeman acknowledges the support from the UMN Undergraduate Research Opportunities Program (UROP). H. Zhang acknowledges the support from the 3M Science and Technology Doctoral Fellowship, UMII MnDRIVE Graduate Assistantship Award, and Frontera Computational Science Fellowship. The authors acknowledge the computing resources provided by the Minnesota Supercomputing Institute (MSI).

Publisher Copyright:
© 2022, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

Fingerprint

Dive into the research topics of 'Stiffness-reduced neural ode models for data-driven reduced-order modeling of combustion chemical kinetics'. Together they form a unique fingerprint.

Cite this