Combining flamelet-generated manifold and machine learning models in simulation of a non-premixed diffusion flame

作     者：Kaimeng Li Pourya Rahnama Ricardo Novella Bart Somers 

作者机构：Power&Flow–Department of Mechanical Engineering.Technical University of Eindhoven.P.O.Box 5135600 MB EindhovenThe Netherlands CMT–Motores T´ermicos.Universidad Polit´ecnica de Valencia.Camino de Vera s/nE-46022 ValenciaSpain 

出 版 物：《Energy and AI》 (能源与人工智能（英文）)

年 卷 期：2023年第14卷第4期

页      面：173-188页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：This work was funded by the Netherlands Organisation for Scientific Research(NWO project number 14927) 

主　　题：Flamelet models Tabulated chemistry models Computational fluid dynamics Machine learning Non-premixed diffusion flame 

摘      要：Flamelet Generated Manifold(FGM)is an example of a chemistry tabulation or a flamelet method that is under attention because of its accuracy and speed in predicting combustion ***,the main problem in applying the model is a large amount of memory *** way to solve this problem is to apply machine learning(ML)to replace the stored tabulated *** different machine learning methods,including two Artificial Neural Networks(ANNs),a Random Forest(RF),and a Gradient Boosted Trees(GBT),are trained,validated,and compared in terms of various performance *** progress variable source term and transport properties are replaced with the ML *** attention was paid to the progress variable source term due to its high gradient and wide range of its value in the control variables *** preprocessing is shown to play an essential role in improving the performance of the *** ensemble models,namely RF and GBT,exhibit high training efficiency and acceptable *** the other hand,the ANN models have lower training errors and take longer to *** four models are then combined with a one-dimensional combustion code to simulate a counterflow non-premixed diffusion flame in engine-relevant *** predictions of the ML-FGM models are compared with detailed chemical simulations and the original FGM model for key combustion properties and representative species profiles.