...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Combustion and Flame >Machine learning tabulation of thermochemistry in turbulent combustion: An approach based on hybrid flamelet/random data and multiple multilayer perceptrons
【24h】

Machine learning tabulation of thermochemistry in turbulent combustion: An approach based on hybrid flamelet/random data and multiple multilayer perceptrons

机译：Machine learning tabulation of thermochemistry in turbulent combustion: An approach based on hybrid flamelet/random data and multiple multilayer perceptrons

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相关主题

摘要

A new machine learning methodology is proposed for speeding up thermochemistry computations insimulations of turbulent combustion. The approach is suited to a range of methods including Direct NumericalSimulation (DNS), Probability Density Function (PDF) methods, unsteady flamelet, ConditionalMoment Closure (CMC), Multiple Mapping Closure (MMC), Linear Eddy Model (LEM), Thickened FlameModel, the Partially Stirred Reactor (PaSR) method (as in OpenFOAM) and the computation of laminarflames. In these methods, the chemical source term must be evaluated at every time step, and is oftenthe most expensive element of a simulation. The proposed methodology has two main objectives: to offerenhanced capacity for generalisation and to improve the accuracy of the ANN prediction. To accomplishthe first objective, we propose a hybrid flamelet/random data (HFRD) method for generating the trainingset. The random element endows the resulting ANNs with increased capacity for generalisation. Regardingthe second objective, a multiple multilayer perceptron (MMP) approach is developed where differentmultilayer perceptrons (MLPs) are trained to predict states that result in smaller or larger compositionchanges, as these states feature different dynamics. It is shown that the multiple MLP method can greatlyreduce the prediction error, especially for states yielding small composition changes. The approach is usedto simulate flamelets of varying strain rates, one-dimensional premixed flames with differential diffusionand varying equivalence ratio, and finally the Large Eddy Simulation (LES) of CH 4 /air piloted flames SandiaD, E and F, which feature different levels of local extinction. The simulation results show very goodagreement with those obtained from direct integration, while the range of problems simulated indicatesthat the approach has great capacity for generalisation. Finally, a speed-up ratio of 12 is attained for thereaction step.

著录项

获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号