西安交通大学动力工程多相流国家重点实验室
纸质出版:2023
移动端阅览
殷阁媛, 肖波, 胡二江, 等. 采用神经网络与贝叶斯反演法自动优化乙酸化学反应动力学模型[J]. 西安交通大学学报, 2023,(7):130-138.
为了解决传统化学反应动力学模型构建效率低、不确定度无法准确衡量的问题,提出了基于实验数据驱动的模型智能化构建方法。利用人工神经网络和马尔可夫蒙特卡罗链加速贝叶斯反演法的求解,基于层流火焰速度实验数据自动优化乙酸模型。仿真结果表明:通过增加神经网络样本数和隐藏层数使测试集的误差小于1%
满足化学反应动力学替代模型的要求;神经网络能够产生大量样本,有效减少马尔可夫链取样过程的误差以提高收敛效率;利用层流火焰速度实验数据约束后,反应CH
2
CO
2
H+H=CH
2
CO+H
2
O的速率常数的后验概率相对于先验概率发生了显著变化,均值在优化后增大了10倍,误差明显减小,该反应对乙酸层流速度的影响最为显著;优化后的化学反应动力学模型能够准确预测不同温度下的层流火焰速度,并且约束后的模型不确定度明显降低。研究结果可为化学反应动力学模型的实际工程应用提供参考。
Wang,Zhou,Lin,Law,Yang.Facilitating Bayesian analysis of combustion kinetic models with artificial neural network[J].Combustion and Flame,2020.
Institute of Chemistry, Eötvös Loránd University (ELTE), Pázmány Péter sétány 1/A, 1117 Budapest, Hungary,MTA-ELTE Research Group on Complex Chemical Systems, Pázmány Péter sétány 1/A, 1117 Budapest, Hungary,Institute of Chemistry, Eötvös Loránd University (ELTE), Pázmány Péter sétány 1/A, 1117 Budapest, Hungary,MTA-ELTE Research Group on Complex Chemical Systems, Pázmány Péter sétány 1/A, 1117 Budapest, Hungary,Institute of Chemistry, Eötvös Loránd University (ELTE), Pázmány Péter sétány 1/A, 1117 Budapest, Hungary,MTA-ELTE Research Group on Complex Chemical Systems, Pázmány Péter sétány 1/A, 1117 Budapest, Hungary,Combustion Chemistry Centre, National University of Ireland Galway (NUIG), Galway, Republic of Ireland,Institute of Chemistry, Eötvös Loránd University (ELTE), Pázmány Péter sétány 1/A, 1117 Budapest, Hungary.Uncertainty quantification of a newly optimized methanol and formaldehyde combustion mechanism[J].Combustion and Flame,2017.
Okjoo Park,Peter S. Veloo,David A. Sheen,Yujie Tao,Fokion N. Egolfopoulos,Hai Wang.Chemical kinetic model uncertainty minimization through laminar flame speed measurements[J].Combustion and Flame,2016.
Fabrizio Bisetti,Daesang Kim,Omar Knio,Quan Long,Raul Tempone.Optimal Bayesian Experimental Design for Priors of Compact Support with Application to Shock‐Tube Experiments for Combustion Kinetics[J].International Journal for Numerical Methods in Engineering,2016.
Moah Christensen,Alexander A. Konnov.Laminar burning velocity of acetic acid + air flames[J].Combustion and Flame,2016.
T. Varga,T. Nagy,C. Olm,I.Gy. Zsély,R. Pálvölgyi,É. Valkó,G. Vincze,M. Cserháti,H.J. Curran,T. Turányi.Optimization of a hydrogen combustion mechanism using both direct and indirect measurements[J].Proceedings of the Combustion Institute,2015.
Xiaoyu Li,Xiaoqing You,Fujia Wu,Chung K. Law.Uncertainty analysis of the kinetic model prediction for high-pressure H 2 /CO combustion[J].Proceedings of the Combustion Institute,2015.
Hai Wang,David A. Sheen.Combustion kinetic model uncertainty quantification, propagation and minimization[J].Progress in Energy and Combustion Science,2015.
Nikhil Galagali,Youssef M. Marzouk.Bayesian inference of chemical kinetic models from proposed reactions[J].Chemical Engineering Science,2015.
Kalen Braman,Todd A. Oliver,Venkat Raman.Bayesian analysis of syngas chemistry models[J].Combustion Theory and Modelling,2013.
Xun Huan,Youssef M. Marzouk.Simulation-based optimal Bayesian experimental design for nonlinear systems[J].Journal of Computational Physics,2013.
Green W. H.,Barton P. I.,Bhattacharjee B.,Matheu D. M.,Schwer D. A.,Song J.,Sumathi R.,Carstensen H. H.,Dean A. M.,Grenda J. M..Computer Construction of Detailed Chemical Kinetic Models for Gas-Phase Reactors[J].Industrial & Engineering Chemistry Research,2001.
A. Chebbi,P. Carlier.Carboxylic acids in the troposphere, occurrence, sources, and sinks: A review[J].Atmospheric Environment,1996(24).
Lawrence J E,Koutrakis P.Measurement of atmospheric formic and acetic acids: methods evaluation and results from field studies.[J].Environmental science & technology,1994(5).
R. W. Talbot,K. M. Beecher,R. C. Harriss,W. R. Cofer.Atmospheric geochemistry of formic and acetic acids at a mid‐latitude temperate site[J].Journal of Geophysical Research: Atmospheres,1988(D2).
Kawamura K,Ng L L,Kaplan I R.Determination of organic acids (C1-C10) in the atmosphere, motor exhausts, and engine oils.[J].Environmental science & technology,1985(11).
马海辉,余小玲,吕倩,叶君超.一维卷积神经网络在往复式压缩机气阀故障诊断中的应用[J].西安交通大学学报,2022(04).
李怡昕,胡桥,刘钰,杨倩.水下航行器仿生侧线探测阵列优化布置模型及评估方法[J].西安交通大学学报,2021(11).
吕恩雨,马志豪,王鑫,董永超,李新,金亦凡.乙醇和二甲醚在激波管内的裂解试验与动力学研究[J].西安交通大学学报,2021(11).
徐宏明,周泉.人工智能在发动机控制开发中的应用及前景[J].汽车安全与节能学报,2021(02).
李威,张哲巅.某航空发动机燃烧室天然气湿燃烧数值模拟研究[J].热能动力工程,2021(05).
钟建华,齐乐华,李妙玲,赵志龙,李贺军.利用人工神经网络的偏光下热解炭织构类型识别[J].西安交通大学学报,2010(07).
0
浏览量
16
下载量
1
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621