Data-Driven Tabulation for Chemistry Integration Using Recurrent Neural Networks
Data-Driven Tabulation for Chemistry Integration Using Recurrent Neural Networks
复制标题
使用循环神经网络进行化学集成的数据驱动制表
DOI：
10.1109/tnnls.2022.3175301
复制
发表时间：
2022-06
影响因子：
10.4
通讯作者：
Qian Feng
中科院分区：
文献类型：
--
作者：
Zhang Yu;Lin Qingguo;Du Wenli;Qian Feng
由于描述化学反应动力学的常微分方程（ODE）涉及广泛的时间尺度，使用详细燃烧机制对化学反应流进行多维数值模拟的计算成本很高。针对这一问题，本文提出了一种经济的数据驱动的快速燃烧化学集成的制表算法。它使用递归神经网络（RNN）来构建从一系列当前和过去状态到下一个状态的表格，充分利用RNN处理时间序列数据的长期依赖性。训练数据首先由直接数值积分生成，形成初始状态空间，该初始状态空间由K-means算法划分为若干子区域。同时也确定了每个聚类的质心。接下来，在每个子区域中构造Elman RNN来近似昂贵的直接积分，其中从质心获得的积分例程被视为存储和检索常微分方程解的基础。最后，使用具有主成分分析（PCA）的α形度量来生成一组降阶几何约束，其表征这些RNN近似的适用范围。对于在线实现，经常验证几何约束以确定使用哪个RNN网络来近似积分例程。所提出的算法的优点是使用一组RNN来代替昂贵的直接积分，这允许减少内存消耗和计算成本。H2/CO-空气燃烧过程的数值模拟进行了比较，现有的ODE求解器证明所提出的算法的有效性。
Due to the wide range of time scales involved in the ordinary differential equations (ODEs) describing chemical reaction kinetics, multidimensional numerical simulation of chemical reactive flows using detailed combustion mechanisms is computationally expensive. To confront this issue, this article presents an economic data-driven tabulation algorithm for fast combustion chemistry integration. It uses the recurrent neural networks (RNNs) to construct the tabulation from a series of current and past states to the next state, which takes full advantage of RNN in handling long-term dependencies of time series data. The training data are first generated from direct numerical integrations to form an initial state space, which is divided into several subregions by the K-means algorithm. The centroid of each cluster is also determined at the same time. Next, an Elman RNN is constructed in each of these subregions to approximate the expensive direct integration, in which the integration routine obtained from the centroid is regarded as the basis for a storing and retrieving solution to ODEs. Finally, the alpha-shape metrics with principal component analysis (PCA) are used to generate a set of reduced-order geometric constraints that characterize the applicable range of these RNN approximations. For online implementation, geometric constraints are frequently verified to determine which RNN network to be used to approximate the integration routine. The advantage of the proposed algorithm is to use a set of RNNs to replace the expensive direct integration, which allows to reduce both the memory consumption and computational cost. Numerical simulations of a H2/CO-air combustion process are performed to demonstrate the effectiveness of the proposed algorithm compared to the existing ODE solver.
登录
查看更多内容
影响因子：
4.4
作者：
Zhaoyu Luo;C. Yoo;E. Richardson;Jacqueline H. Chen;C. Law;T. Lu
通讯作者：
Zhaoyu Luo;C. Yoo;E. Richardson;Jacqueline H. Chen;C. Law;T. Lu
影响因子：
4.4
作者：
Zhuyin Ren;Yufeng Liu;T. Lu;L. Lu;O. Oluwole;G. Goldin
通讯作者：
Zhuyin Ren;Yufeng Liu;T. Lu;L. Lu;O. Oluwole;G. Goldin
DOI：
10.1007/s00371-003-0207-1
发表时间：
2003-12
期刊：
The Visual Computer
影响因子：
--
作者：
Xiaolong Xu;K. Harada
通讯作者：
Xiaolong Xu;K. Harada
具有刚度的随机化学系统的计算奇异摄动分析
影响因子：
4.1
作者：
Wang Lijin;Han Xiaoying;Cao Yanzhao;Najm Habib N
通讯作者：
Najm Habib N
影响因子：
2.5
作者：
EDELSBRUNNER, H;KIRKPATRICK, DG;SEIDEL, R
通讯作者：
SEIDEL, R