Interpretable data-driven methods for subgrid-scale closure in LES for transcritical LOX/GCH4 combustion
Interpretable data-driven methods for subgrid-scale closure in LES for transcritical LOX/GCH4 combustion
复制标题
DOI：
10.1016/j.combustflame.2021.111758
复制
发表时间：
2022-05-09
影响因子：
4.4
通讯作者：
Ihme, Matthias
中科院分区：
文献类型：
--
作者：
Chung, Wai Tong;Mishra, Aashwin Ananda;Ihme, Matthias
尽管数据驱动的方法作为模拟湍流火焰的闭合模型表现出了很高的准确性，但这些模型经常因缺乏物理可解释性而受到批评，其中它们提供了答案，但没有深入了解其基本原理。在这项工作中，我们证明了两种可解释的机器学习算法，即随机森林回归器和稀疏符号回归，可以为发现湍流跨临界火焰的亚网格尺度（SGS）项的解析表达式提供机会。这些跨临界条件存在于各种在高压下运行的燃烧系统中，这些系统超过了燃料-氧化剂混合物的热力学临界极限，并且需要考虑复杂的流体行为，这可能会对大涡模拟中现有的亚网格规模（SGS）模型的有效性产生怀疑。为此，对跨临界液氧/气态甲烷 (LOX/GCH4) 惰性流和反应流进行直接数值模拟 (DNS)。使用该数据，对 Favre 过滤的 DNS 数据进行先验分析，以比较随机森林 SGS 模型与传统基于物理的 SGS 模型的准确性。使用梯度模型计算的 SGS 应力与从过滤的 DNS 中提取的精确项具有良好的一致性。结果表明，在对子网格应力进行建模、在具有足够代表性的数据库上进行训练并选择适当的特征集时，随机森林可以与代数模型一样有效。随机森林特征重要性评分的使用表明能够通过稀疏符号回归发现亚网格尺度应力的分析模型。通过对亚网格尺度温度进行建模，证明了随机森林和稀疏符号回归的普遍性，亚网格尺度温度是通过过滤非线性真实流体状态方程而产生的一项，具有良好的准确性。(c) 2021 年燃烧研究所。由爱思唯尔公司出版。保留所有权利。
Although data-driven methods have shown high accuracy as closure models for simulating turbulent flames, these models are often criticized for lack of physical interpretability, wherein they provide answers but no insight into their underlying rationale. In this work, we show that two interpretable machine learning algorithms, namely the random forest regressor and the sparse symbolic regression, can offer opportunities for discovering analytic expressions for subgrid-scale (SGS) terms of a turbulent transcritical flame. These transcritical conditions are found in various combustion systems that operate under high pressures that surpass the thermodynamic critical limit of fuel-oxidizer mixtures, and require the consideration of complex fluid behaviors that can cast doubts on the validity of existing subgrid-scale (SGS) models in large-eddy simulations. To this end, direct numerical simulations (DNS) of transcritical liquid-oxygen/gaseous-methane (LOX/GCH4) inert and reacting flows are performed. Using this data, a priori analysis is performed on the Favre-filtered DNS data to compare the accuracy of random forest SGS-models with conventional physics-based SGS-models. SGS stresses calculated with the gradient model are shown to have good agreement with the exact terms extracted from filtered DNS. Results demonstrate that random forests can perform as effectively as algebraic models when modeling subgrid stresses, when trained on a sufficiently representative database and with a suitable choice of the feature set. The employment of the random forest feature importance score is shown to enable the discovery of a analytic model for subgrid-scale stresses through sparse symbolic regression. The generalizability of random forest and sparse symbolic regression is demonstrated by modeling the subgrid-scale temperature, a term that arises from filtering the non-linear real-fluid equation-of-state, with good accuracy.(c) 2021 The Combustion Institute. Published by Elsevier Inc. All rights reserved.