Explore artificial neural networks for solving complex hydrocarbon chemistry in turbulent reactive flows
作者机构：Institte for Aero EngineTsinghua UniversitBejing 100084China Seience and Technology on CombustionInternal Flow and Thermal-structure LaboratoryNorthwesterm Polytechnical UniversityXi'an 710072China
出 版 物：《Fundamental Research》 (自然科学基础研究（英文版）)
年 卷 期：2022年第2卷第4期
页 面：595-603页
学科分类：080704[工学-流体机械及工程] 080103[工学-流体力学] 08[工学] 0807[工学-动力工程及工程热物理] 0801[工学-力学（可授工学、理学学位）]
基 金：supported by the National Natural Science Foundation of China(Grant No.52025062) Simulations are performed with the computational resources from the Tsinghua National Laboratory for Information Science and Technology
主 题：Chemical kinetics Turbulent combustion Artificial neural network Machine learning Numerical simulation
摘 要：Global warming caused by the use of fossil fuels is a common concern of the world *** is of practical importance to conduct in-depth fundamental research and optimal design for modern engine combustors through However,complex hydrocarbon chemistry,an indispensable component for predictive modeling,is computahigh-fidelity computational fluid dynamics(CFD),so as to achieve energy conservation and emission *** demanding,Its application in simulation-based design optimization,although desirable,is quite *** address this challenge,we propose a methodology for representing complex chemistry with artificial neural networks(ANNs),which are trained with a comprehensive sample dataset generated by the Latin hypercube sampling(LHS)*** a given chemical kinetic mechanism,the thermochemical sample data is able to cover the whole accessible pressure/temperature/species space in various turbulent *** ANN-based model consists of two different layers:the self-organizing map(SOM)and the back-propagation neural network(BPNN).The methodology is demonstrated to represent a 30-species methane chemical *** obtained ANN model is applied to simulate both a non-premixed turbulent flame(DLR_A)and a partially premixed turbulent flame(Flame D)to validate its applicability for different *** show that the ANN-based chemical kinetics can reduce the computational cost by about two orders of magnitude without loss of accuracy,The proposed methodology can successfully construct an ANN-based chemical mechanism with significant ffciency gain and a broad scope of applicability,and thus holds a great potential for complex hydrocarbon fuels.
维普期刊数据库