题目：利用基于非预混-微混合模型的机器学习方法简化化学反应机理：以侧壁作用下的湍流混合全氧火焰DNS为例
摘要：文本提出了一种利用机器学习简化化学反应机理的方法，并将其应用于一个针对冷却侧壁作用下的湍流混合全氧火焰的直接数值模拟。神经网络（ANN）的训练及后续应用主要根据：处理由物种质量分数和温度组成的“热化学向量”（ANN输入），以预测相应的化学源相（ANN输出）。ANN的训练与流动解耦，是基于详细化学反应的湍流的非绝热非预混合微混合的典型算例，考虑热损失。之后，在一个二维DNS中，利用详细化学反应机理和一个针对本工况专门开发的简化机理对机器学习模型进行后验。随后，使用ANN或简化化学反应机理进行三维DNS，以进行额外的后验性测试。基于ANN的简化化学方法与基于Arrhenius的详细和简化的反应机理的一致性较好，在与DNS耦合的条件下，CPU用时比详细机理快25倍，比简化机机理快3倍。该方法的主要潜力在于它的数据驱动特性和对刚醒化学源相的处理。 前者可以针对特定要求自动并快速生成简化的化学反应机理。 后者避免了Arrhenius反应速率的计算，也避免了对刚性化学源相的直接积分，这都显著减小了仿真所需的CPU时间。
Notes:
- 为了避免过拟合，保证质量守恒的条件下，在DNS数据中加入2%和3%的噪声
- 为了解决中间产物，如H2O2，质量分数数据阶跃的问题，在0到最大值之间人工加入若干随机数据，并将其他数据按比例缩放，然后带入详细机理求解源相
- ANN的输入：质量分数及温度，输出化学反应源相 \omega_i = (\phi_i(t+\delta t)-\phi_i(t))/\delta t, \delta t = 3E-7s，为本文中流动的求解的时间步长
Instantaneous iso-surface of Q crite rion [38] predicted by ANN-DNS: Q = 10^7 s−2, colored by gas temperature. Top graph: distribution of instantaneous wall temperature along the centerline.
Sketch of the ANN training process from the micro-mixing database. (For interpretation of the references to color in this figure, the reader is referred to the web version of this article.)
Title: Chemistry reduction using machine learning trained from non-premixed micro-mixing modeling: Application to DNS of a syngas turbulent oxy-flame with side-wall effects
Abstract: A chemistry reduction approach based on machine learning is proposed and applied to direct numerical simulation (DNS) of a turbulent non-premixed syngas oxy-flame interacting with a cooled wall. The training and the subsequent application of artificial neural networks (ANNs) rely on the processing of ‘thermochemical vectors’ composed of species mass fractions and temperature (ANN input), to predict the corresponding chemical sources (ANN output). The training of the ANN is performed aside from any flow simulation, using a turbulent non-adiabatic non-premixed micro-mixing based canonical problem with a reference detailed chemistry. Heat-loss effects are thus included in the ANN training. The performance of the ANN chemistry is then tested a-posteriori in a two-dimensional DNS against the detailed mechanism and a reduced mechanism specifically developed for the operating conditions considered. Then, three-dimensional DNS are performed either with the ANN or the reduced chemistry for additional a-posteriori tests. The ANN reduced chemistry achieves good agreement with the Arrhenius-based detailed and reduced mechanisms, while being in terms of CPU cost 25 times faster than the detailed mechanism and 3 times faster than the reduced mechanism when coupled with DNS. The major potential of the method lies both in its data driven character and in the handling of the stiff chemical sources. The former allows for easy implementation in the context of automated generation of case-specific reduced chemistry. The latter avoids the Arrhenius rates calculation and also the direct integration of stiff chemistry, both leading to a significant CPU time reduction.
原文链接, CNF, IF 4.57
相关文献
