Machine learning for integrating combustion chemistry in numerical simulations
| Autor: | Phuc-Danh Nguyen, Pascale Domingo, Luc Vervisch, Huu-Tri Nguyen |
|---|---|
| Přispěvatelé: | Complexe de recherche interprofessionnel en aérothermochimie (CORIA), Université de Rouen Normandie (UNIROUEN), Normandie Université (NU)-Normandie Université (NU)-Institut national des sciences appliquées Rouen Normandie (INSA Rouen Normandie), Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS), ArcelorMittal Maizières Research SA, ArcelorMittal |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Artificial neural network
Degrees of freedom (statistics) Principal component analysis 02 engineering and technology Machine learning computer.software_genre Combustion 01 natural sciences 7. Clean energy 010305 fluids & plasmas Reduction (complexity) [SPI]Engineering Sciences [physics] QA76.75-76.765 Combustion chemistry 0203 mechanical engineering Artificial Intelligence 0103 physical sciences Decomposition (computer science) Computer software Physics::Chemical Physics Engineering (miscellaneous) ComputingMilieux_MISCELLANEOUS Partial differential equation Chemistry reduction Computer simulation business.industry k-means clustering TK1-9971 020303 mechanical engineering & transports General Energy Micro-mixing modeling Artificial intelligence Electrical engineering. Electronics. Nuclear engineering business computer |
| Zdroj: | Energy and AI, Vol 5, Iss, Pp 100082-(2021) Energy and AI Energy and AI, 2021, 5, pp.100082. ⟨10.1016/j.egyai.2021.100082⟩ |
| ISSN: | 2666-5468 |
| DOI: | 10.1016/j.egyai.2021.100082⟩ |
| Popis: | A strategy based on machine learning is discussed to close the gap between the detailed description of combustion chemistry and the numerical simulation of combustion systems. Indeed, the partial differential equations describing chemical kinetics are stiff and involve many degrees of freedom, making their solving in three-dimensional unsteady simulations very challenging. It is discussed in this work how a reduction of the computing cost by an order of magnitude can be achieved using a set of neural networks trained for solving chemistry. The thermochemical database used for training is composed of time evolutions of stochastic particles carrying chemical species mass fractions and temperature according to a turbulent micro-mixing problem coupled with complex chemistry. The novelty of the work lies in the decomposition of the thermochemical hyperspace into clusters to facilitate the training of neural networks. This decomposition is performed with the Kmeans algorithm, a local principal component analysis is then applied to every cluster. This new methodology for combustion chemistry reduction is tested under conditions representative of a non-premixed syngas oxy-flame. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|