Machine Learning

Accelerating Combustion Simulations with Machine Learning Surrogate Models
Machine learning surrogate models for efficient combustion simulations.
Anuj Kumar
PDF Cite Source Document DOI
Accelerating Combustion Simulations with Machine Learning Surrogate Models
Combustion chemistry acceleration with DeepONets
A combustion chemistry acceleration scheme for implementation in reacting flow simulations is developed based on deep operator nets …
Anuj Kumar, Tarek Echekki
Cite Video Source Document DOI
Combustion chemistry acceleration with DeepONets
A Physics-Constrained NeuralODE Approach for Robust Learning of Stiff Chemical Kinetics
The high computational cost associated with solving for detailed chemistry poses a significant challenge for predictive computational …
Tadbhagya Kumar, Anuj Kumar, Pinaki Pal
Cite Source Document
A Physics-Constrained NeuralODE Approach for Robust Learning of Stiff Chemical Kinetics
Physics - Informed Machine Learning for Reduced Space Chemical Kinetics
Modeling detailed chemical kinetics stands as a primary challenge in combustion simulations. Recent machine learning (ML) approaches …
Anuj Kumar, Tarek Echekki
Cite Source Document
Physics - Informed Machine Learning for Reduced Space Chemical Kinetics
On the application of principal component transport for compression ignition of lean fuel/air mixtures under engine relevant conditions
Principal component transport-based data-driven reduced-order models (PC-transport ROM) are being increasingly adopted as a combustion …
Ki Sung Jung, Anuj Kumar, Tarek Echekki, Jacqueline H. Chen
Cite Source Document DOI
On the application of principal component transport for compression ignition of lean fuel/air mixtures under engine relevant conditions
Acceleration of turbulent combustion DNS via principal component transport
We investigate the implementation of principal component (PC) transport to accelerate the direct numerical simulation (DNS) of …
Anuj Kumar, Martin Rieth, Opeoluwa Owoyele, Jacqueline H. Chen, Tarek Echekki
Cite Source Document DOI
Acceleration of turbulent combustion DNS via principal component transport
A Framework for Combustion Chemistry Acceleration with DeepONets
A combustion chemistry acceleration scheme is developed based on deep operator networks (DeepONets). The scheme is based on the …
Anuj Kumar, Tarek Echekki
Cite Video Source Document
A Framework for Combustion Chemistry Acceleration with DeepONets