Machine learning for integrating combustion chemistry in numerical simulations  

作　　者：Huu-Tri Nguyen Pascale Domingo Luc Vervisch Phuc-Danh Nguyen 

机构地区：[1]CORIA-CNRS,Normandie Université,INSA Rouen Normandie,Saint-Etienne-du-Rouvray 76801,France [2]ArcelorMittal Global Research and Development,Maiziéres-lés-Metz 57280,France

出　　处：《Energy and AI》2021年第3期330-338,共9页能源与人工智能（英文）

基　　金：The Ph.D.of the first author is funded by ANRT(Agence Nationale de la Recherche et de la Technology)and ArcelorMittal under the CIFRE no.2019/0056.

摘　　要：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 describ-ing chemical kinetics are stiffand 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 ther-mochemical 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.

关 键 词：Combustion chemistry Micro-mixing modeling Principal component analysis Artificial neural network Chemistry reduction 

分 类 号：O64[理学—物理化学]