Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A graph neural network based chemical mechanism reduction method for combustion applications

Manuru Nithin Padiyar, Priyabrat Dash, Konduri Aditya

Abstract

Direct numerical simulations of turbulent reacting flows involving millions of grid points and detailed chemical mechanisms with hundreds of species and thousands of reactions are computationally prohibitive. To address this challenge, we present two data-driven chemical mechanism reduction formulations based on graph neural networks (GNNs) with message-passing transformer layers that learn nonlinear dependencies among species and reactions. The first formulation, GNN-SM, employs a pre-trained surrogate model to guide reduction across a broad range of reactor conditions. The second formulation, GNN-AE, uses an autoencoder formulation to obtain highly compact mechanisms that remain accurate within the thermochemical regimes used during training. The approaches are demonstrated on detailed mechanisms for methane (53 species, 325 reactions), ethylene (96 species, 1054 reactions), and iso-octane (1034 species, 8453 reactions). GNN-SM achieves reductions comparable to the established graph-based method DRGEP while maintaining accuracy across a wide range of thermochemical states. In contrast, GNN-AE achieves up to 95% reduction in species and reactions and outperforms DRGEP within its target conditions. Overall, the proposed framework provides an automated, machine-learning-based pathway for chemical mechanism reduction that can complement traditional expert-guided analytical approaches.

A graph neural network based chemical mechanism reduction method for combustion applications

Abstract

Direct numerical simulations of turbulent reacting flows involving millions of grid points and detailed chemical mechanisms with hundreds of species and thousands of reactions are computationally prohibitive. To address this challenge, we present two data-driven chemical mechanism reduction formulations based on graph neural networks (GNNs) with message-passing transformer layers that learn nonlinear dependencies among species and reactions. The first formulation, GNN-SM, employs a pre-trained surrogate model to guide reduction across a broad range of reactor conditions. The second formulation, GNN-AE, uses an autoencoder formulation to obtain highly compact mechanisms that remain accurate within the thermochemical regimes used during training. The approaches are demonstrated on detailed mechanisms for methane (53 species, 325 reactions), ethylene (96 species, 1054 reactions), and iso-octane (1034 species, 8453 reactions). GNN-SM achieves reductions comparable to the established graph-based method DRGEP while maintaining accuracy across a wide range of thermochemical states. In contrast, GNN-AE achieves up to 95% reduction in species and reactions and outperforms DRGEP within its target conditions. Overall, the proposed framework provides an automated, machine-learning-based pathway for chemical mechanism reduction that can complement traditional expert-guided analytical approaches.
Paper Structure (9 sections, 6 equations, 8 figures, 3 tables)

This paper contains 9 sections, 6 equations, 8 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Methodology
  3. GNN reduction methodology
  4. Network architectures
  5. Results
  6. Methane oxidation
  7. Ethylene oxidation
  8. Iso-octane oxidation
  9. Conclusions

Figures (8)

  • Figure 1: A flowchart representation of the (a) GNN-SM implementation, (b) GNN-AE implementation along with graphs of the (c) input and (d) output mechanisms.
  • Figure 2: Temporal evolution of temperature and heat release rate at initial temperatures of (a) 1500K and (b) 1000K for methane oxidation.
  • Figure 3: Temporal evolution of scaled species mole fractions at initial temperature of 1500K for methane oxidation.
  • Figure 4: Validation of ignition delay times for the reduced methane mechanisms over a range of initial temperatures and pressures.
  • Figure 5: Temporal evolution of temperature and heat release rate at initial temperatures of (a) 1500K and (b) 1200K for ethylene oxidation.
  • ...and 3 more figures