Artificial neural network based chemical mechanisms for computationally efficient modeling of hydrogen/carbon monoxide/kerosene combustion

被引:49
作者
An, Jian [1 ,2 ]
He, Guoqiang [1 ]
Luo, Kaihong [2 ]
Qin, Fei [1 ]
Liu, Bing [1 ]
机构
[1] Northwestern Polytech Univ, Internal Flow & Thermal Struct Lab, Sci & Technol Combust, Xian 710072, Shaanxi, Peoples R China
[2] UCL, Dept Mech Engn, London WC1E 7JE, England
基金
英国工程与自然科学研究理事会;
关键词
Hydrogen combustion; Kerosene combustion; Supersonic combustion; Artificial neural network (ANN); Rocket-based combined cycle (RBCC); DYNAMIC ADAPTIVE CHEMISTRY; PEM FUEL-CELL; PDF SIMULATION; ANN; IMPLEMENTATION; TABULATION; OSCILLATION; PREDICTION; STRATEGY; SCHEME;
D O I
10.1016/j.ijhydene.2020.08.081
中图分类号
O64 [物理化学(理论化学)、化学物理学];
学科分类号
070304 ; 081704 ;
摘要
To effectively simulate the combustion of hydrogen/hydrocarbon-fueled supersonic engines, such as scramjet and rocket-based combined cycle (RBCC) engines, a detailed mechanism for chemistry is usually required but computationally prohibitive. In order to accelerate chemistry calculation, an artificial neural network (ANN) based methodology was introduced in this study. This methodology consists of two different layers: self-organizing map (SOM) and back-propagation neural network (BPNN). The SOM is for clustering the dataset into subsets to reduce the nonlinearity, while the BPNN is for regression for each subset. Compared with previous studies, the chemical reaction mechanism involved in this study is more complex, therefore, the particle swarm optimization (PSO) method is employed for accelerating training process in this study. Then we were committed to constructing an ANN-based mechanism of hydrogen and kerosene for supersonic turbulent combustion and verifying it in a practical RBCC combustion chamber. The training data was generated by RANS simulations of the RBCC combustion chamber, and then fed into the SOM-BPNN with six different topologies (three different SOM topologies and two different BPNN topologies). Through LES simulation of the Rocket-Based Combined Cycle (RBCC) combustor, the six ANN-based mechanisms were verified. By comparing the predicted results of six cases with those of the conventional ODE solver, it is found that if the topology is properly designed, high-precision results in terms of ignition, quenching and mass fraction prediction can be achieved. As for efficiency, 8 similar to 20 times speedup of the chemical system integration was achieved, which will greatly improve the computational efficiency of combustion simulation of hydrogen/carbon monoxide/kerosene mixture. Crown Copyright (C) 2020 Published by Elsevier Ltd on behalf of Hydrogen Energy Publications LLC. All rights reserved.
引用
收藏
页码:29594 / 29605
页数:12
相关论文
共 43 条
[1]   A deep learning framework for hydrogen-fueled turbulent combustion simulation [J].
An, Jian ;
Wang, Hanyi ;
Liu, Bing ;
Luo, Kai Hong ;
Qin, Fei ;
He, Guo Qiang .
INTERNATIONAL JOURNAL OF HYDROGEN ENERGY, 2020, 45 (35) :17992-18000
[2]   Dynamic adaptive chemistry with mechanisms tabulation and in situ adaptive tabulation (ISAT) for computationally efficient modeling of turbulent combustion [J].
An, Jian ;
He, Guoqiang ;
Qin, Fei ;
Wei, Xianggeng ;
Liu, Bing .
COMBUSTION AND FLAME, 2019, 206 :467-475
[3]   Modelling the temporal evolution of a reduced combustion chemical system with an artificial neural network [J].
Blasco, JA ;
Fueyo, N ;
Dopazo, C ;
Ballester, J .
COMBUSTION AND FLAME, 1998, 113 (1-2) :38-52
[4]   A self-organizing-map approach to chemistry representation in combustion applications [J].
Blasco, JA ;
Fueyo, N ;
Dopazo, C ;
Chen, JY .
COMBUSTION THEORY AND MODELLING, 2000, 4 (01) :61-76
[5]   Big Data: A Parallel Particle Swarm Optimization-Back-Propagation Neural Network Algorithm Based on MapReduce [J].
Cao, Jianfang ;
Cui, Hongyan ;
Shi, Hao ;
Jiao, Lijuan .
PLOS ONE, 2016, 11 (06)
[6]   A review on hydrogen industrial aerospace applications [J].
Cecere, D. ;
Giacomazzi, E. ;
Ingenito, A. .
INTERNATIONAL JOURNAL OF HYDROGEN ENERGY, 2014, 39 (20) :10731-10747
[7]   A high-temperature chemical kinetic model for primary reference fuels [J].
Chaos, Marcos ;
Kazakov, Andrei ;
Zhao, Zhenwei ;
Dryer, Frederick L. .
INTERNATIONAL JOURNAL OF CHEMICAL KINETICS, 2007, 39 (07) :399-414
[8]   A chemistry tabulation approach via Rate-Controlled Constrained Equilibrium (RCCE) and Artificial Neural Networks (ANNs), with application to turbulent non-premixed CH4/H2/N2 flames [J].
Chatzopoulos, A. K. ;
Rigopoulos, Stelios .
PROCEEDINGS OF THE COMBUSTION INSTITUTE, 2013, 34 :1465-1473
[9]   PDF MODELING OF TURBULENT NONPREMIXED METHANE JET FLAMES [J].
CHEN, JY ;
KOLLMANN, W ;
DIBBLE, RW .
COMBUSTION SCIENCE AND TECHNOLOGY, 1989, 64 (4-6) :315-346
[10]   Artificial neural network implementation of chemistry with pdf simulation of H-2/CO2 flames [J].
Christo, FC ;
Masri, AR ;
Nebot, EM .
COMBUSTION AND FLAME, 1996, 106 (04) :406-427