The Stabilized Explicit Variable-Load Solver with Machine Learning Acceleration for the Rapid Solution of Stiff Chemical Kinetics

Buchheit, Kyle L.; Owoyele, Opeoluwa; Jordan, Terry G.; Essendelft, Dirk Van

doi:10.48550/arxiv.1905.09395

Cited by 2 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This made the DNN both faster to train and much more accurate, as well as easier to modify. This approach is in line with the work of other authors [41,61,[79][80][81].…”

Section: Deep Neural Network For 1d Sts Euler Shock Flow Relaxationsupporting

confidence: 89%

“…The machine learning solution time tends to diverge as soon as the tolerance is decreased. As already observed in [41,61], this behavior is connected to the nature of the solution methods for initial value problems (IVPs). Stiff chemistry solvers fall into this class, in which the usage of machine learning applied to the primary state variables is difficult but still suitable for secondary property prediction.…”

mentioning

confidence: 73%

See 1 more Smart Citation

Assessment of Machine Learning Methods for State-to-State Approach in Nonequilibrium Flow Simulations

2022

View full text Add to dashboard Cite

State-to-state numerical simulations of high-speed reacting flows are the most detailed but also often prohibitively computationally expensive. In this work, we explore the usage of machine learning algorithms to alleviate such a burden. Several tasks have been identified. Firstly, data-driven machine learning regression models were compared for the prediction of the relaxation source terms appearing in the right-hand side of the state-to-state Euler system of equations for a one-dimensional reacting flow of a N2/N binary mixture behind a plane shock wave. Results show that, by appropriately choosing the regressor and opportunely tuning its hyperparameters, it is possible to achieve accurate predictions compared to the full-scale state-to-state simulation in significantly shorter times. Secondly, several strategies to speed-up our in-house state-to-state solver were investigated by coupling it with the best-performing pre-trained machine learning algorithm. The embedding of machine learning algorithms into ordinary differential equations solvers may offer a speed-up of several orders of magnitude. Nevertheless, performances are found to be strongly dependent on the interfaced codes and the set of variables onto which the coupling is realized. Finally, the solution of the state-to-state Euler system of equations was inferred by means of a deep neural network by-passing the use of the solver while relying only on data. Promising results suggest that deep neural networks appear to be a viable technology also for this task.

show abstract

“…This made the DNN both faster to train and much more accurate, as well as easier to modify. This approach is in line with the work of other authors [41,61,[79][80][81].…”

Section: Deep Neural Network For 1d Sts Euler Shock Flow Relaxationsupporting

confidence: 89%

mentioning

confidence: 73%

Assessment of Machine Learning Methods for State-to-State Approach in Nonequilibrium Flow Simulations

2022

View full text Add to dashboard Cite

show abstract

“…This made the DNN both faster to train and much more accurate, as well as easier to modify. This approach is in line with the work of other authors [55,56,36,57,37].…”

Section: Deep Neural Network For 1d Sts Euler Shock Flow Relaxationsupporting

confidence: 89%

“…Even with relative prediction errors reaching as low as 10 − 5, the solver solution slowly diverges from a physically meaningful value. While it is true that evaluating the ML based predictions are exceptionally quick, the nature of the IVP does not allow for efficient correction of the ML predictions as observed also in [36,37].…”

Section: Matlab-python Interfacementioning

confidence: 99%

Assessment of machine learning methods for state-to-state approaches

Campoli¹,

Кустова²,

Maltseva³

2021

Preprint

View full text Add to dashboard Cite

It is well known that numerical simulations of high-speed reacting flows, in the framework of stateto-state formulations, are the most detailed but also often prohibitively computationally expensive. In this work, we start to investigate the possibilities offered by the use of machine learning methods for state-to-state approaches to alleviate such burden. In this regard, several tasks have been identified. Firstly, we assessed the potential of state-ofthe-art data-driven regression models based on machine learning to predict the relaxation source terms which appear in the right-hand side of the state-to-state Euler system of equations for a onedimensional reacting flow of a N 2 /N binary mixture behind a plane shock wave. It is found that, by appropriately choosing the regressor and opportunely tuning its hyperparameters, it is possible to achieve accurate predictions compared to the full-scale state-to-state simulation in significantly shorter times. Secondly, we investigated different strategies to speed-up our in-house state-to-state solver by coupling it with the best-performing pre-trained machine learning algorithm. The embedding of machine learning methods into ordinary differential equations solvers may offer a speed-up of several orders of magnitude but some care should be paid for how and where such coupling is realized. Performances are found to be strongly dependent on the mutual nature of the interfaced codes. Finally, we aimed at inferring the full solution of the state-to-state Euler system of equations by means of a deep neural network completely by-passing the use of the state-to-state solver while relying only on data. Promising results suggest that deep neural networks appear to be a viable technology also for these tasks.

show abstract

The Stabilized Explicit Variable-Load Solver with Machine Learning Acceleration for the Rapid Solution of Stiff Chemical Kinetics

Cited by 2 publications

References 0 publications

Assessment of Machine Learning Methods for State-to-State Approach in Nonequilibrium Flow Simulations

Assessment of Machine Learning Methods for State-to-State Approach in Nonequilibrium Flow Simulations

Assessment of machine learning methods for state-to-state approaches

Contact Info

Product

Resources

About