Data-driven chemical kinetic reaction mechanism for F-24 jet fuel ignition

Ryu, Je Ir; Kim, Keun Soo; Min, Kyungwook; Scarcelli, Riccardo; Som, Sibendu; Kim, Kenneth S.; Temme, Jacob; Kweon, Chol Bum; Lee, Tonghun

doi:10.1016/j.fuel.2020.119508

Cited by 31 publications

(14 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Following the work of [7], we employ the IDT dataset compiled in [7], including the IDTs of the lean, stoichiometric, and rich F-24/air mixtures measured at 20 bars in a rapid compression machine (RCM) and a shock tube (ST) over the temperature range of 625 K to 1250 K. The RCM is driven pneumatically with a hydraulic stop apparatus, and the initial chamber temperature and pressure are achieved by adjusting the compression ratio [25]. Low-temperature (up to 700 K) IDTs were measured in the RCM.…”

Section: Dataset and Base Modelmentioning

confidence: 99%

“…It has 48 species and 254 reactions. In addition, details of the formulations and stoichiometric coefficients in the F-24 model are the same as in [7], and they are listed in Table 1. For simplicity and consistency, all of the simulations are carried out under constant volume conditions using Arrhenius.jl.…”

Section: Dataset and Base Modelmentioning

confidence: 99%

“…Following the HyChem approach, the 16 steps of the pyrolysis submodel, listed in Table 1, are subject to optimization, and the rest of the core model is fixed. Although in the work of [7], only the pre-factor A and activation energy Ea are optimized, the SGD optimizer can easily scale up to high-dimension, such that all three parameters, including the non-exponential temperature dependence factor b, are optimized. Consequently, the optimization involves 48 parameters.…”

Section: Optimization Techniquesmentioning

confidence: 99%

“…Compared to the species profiles that require expensive laser diagnostic equipment, ignition delay times are easier to measures in shock tubes and rapid compression machines. Therefore, recent work [7] has proposed learning the rate constants of lumped reaction model from an ignition delay times dataset only by employing the stoichiometric coefficients from existing models for similar fuels. However, the base model usually shows large discrepancies in the low-temperature regimes, as the low-temperature chemistry is more fuel-specific compared to high-temperature chemistry.…”

Section: Introductionmentioning

confidence: 99%

“…Thus, one has to optimize the lumped reaction steps from experimental data such that the optimized model can cover both high-and low-temperature regimes. Ryu et al [7] employed genetic algorithms and IDT data to develop a data-driven kinetic model for the Jet fuel of F-24 using the Jet-A HyChem model as the base model. The core of such a data-driven modeling approach is the optimization step using genetic algorithms.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Machine Learning Approaches to Learn HyChem Models

Ji,

Zanders,

Park

et al. 2021

Preprint

View full text Add to dashboard Cite

The HyChem (Hybrid Chemistry) approach has recently been proposed for modeling high-temperature combustion of real, multi-component fuels. The approach combines lumped reaction steps for fuel thermal and oxidative pyrolysis with detailed chemistry for the oxidation of the resulting pyrolysis products. Determining the pyrolysis submodel requires extensive experimentation on speciation measurements. Recent work has been directed to learn HyChem from an existing HyChem model for a similar fuel, which requires less data. However, the approach usually shows substantial discrepancies with experimental data within the Negative Temperature Coefficient (NTC) regime, as the low-temperature chemistry is more fuel-specific than hightemperature chemistry. This paper proposes a machine learning approach to learn the HyChem models that can cover both high-temperature and low-temperature regimes. Specifically, we develop a HyChem model using the experimental datasets of ignition delay times covering a wide range of temperatures and equivalence ratios. The chemical kinetic model is treated as a neural network model, and we then employ stochastic gradient descent (SGD), a technique that was developed for deep learn- * Address all correspondence to this author.ing, for the training. We demonstrate the approach in learning the HyChem model for F-24, which is a Jet-A derived fuel, and compare the results with previous work employing genetic algorithms. The results show that the SGD approach can achieve comparable model performance with genetic algorithms but the computational cost is reduced by 1000 times. In addition, with regularization in SGD, the SGD approach changes the kinetic parameters from their original values much less than genetic algorithm and is thus more likely to retrain mechanistic meanings. Finally, our approach is built upon open-source packages and can be applied to the development and optimization of chemical kinetic models for internal combustion engine simulations.

show abstract

Section: Dataset and Base Modelmentioning

confidence: 99%

Section: Dataset and Base Modelmentioning

confidence: 99%

Section: Optimization Techniquesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations