Kinetics parameter optimization of hydrocarbon fuels via neural ordinary differential equations
Name
CNF_Neural ODE_final.pdf
Description
Accepted version
Size
1.48 MB
Format
Adobe PDF
Checksum (MD5)
f0b046c5bece17ecb8d5c2fb3458fa7a
Author(s)
Su, Xingyu
Ji, Weiqi
An, Jian
Ren, Zhuyin
Deng, Sili
Law, Chung K
Date Issued
May 2023
Journal
Combustion and Flame
Publisher
Elsevier BV
Citation
Su, Xingyu, Ji, Weiqi, An, Jian, Ren, Zhuyin, Deng, Sili et al. 2023. "Kinetics parameter optimization of hydrocarbon fuels via neural ordinary differential equations." Combustion and Flame, 251.
Version
Author's final manuscript
Abstract
Chemical kinetics mechanisms are essential for understanding, analyzing, and simulating complex combustion phenomena. In this study, a neural ordinary differential equation (Neural ODE) framework is employed to optimize the kinetics parameters of reaction mechanisms. Given experimental or high-cost simulated observations as training data, the proposed algorithm can optimally recover the hidden characteristics in the data. Different datasets of various sizes, types, and noise levels are systematically tested. A classic toy problem of stiff Robertson ODE is first used to demonstrate the learning capability, efficiency, and robustness of the Neural ODE approach. A 41-species, 232-reactions JP-10 skeletal mechanism and a 34-species, 121-reactions n-heptane skeletal mechanism are then optimized with species' temporal profiles and ignition delay times, respectively. Results show that the proposed algorithm can optimize stiff chemical models with sufficient accuracy, efficiency and robustness. It is noted that the trained mechanism not only fits the data perfectly but also retains its physical interpretability, which can be further integrated and validated in practical turbulent combustion simulations. In addition, as demonstrated with the stiff Robertson problem, it is promising to adopt Bayesian inference techniques with Neural ODE to estimate the kinetics parameter uncertainties from experimental data.
MIT Department
Massachusetts Institute of Technology. Department of Mechanical Engineering
Terms of Use
Creative Commons Attribution-Noncommercial-ShareAlike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1016/j.combustflame.2023.112732
