Bayesian Analysis of Combustion Kinetic Models for Ammonia-Hydrogen Fuel Blends Using Artificial Neural Networks
Uncertainty quantification (UQ) plays a crucial role in predictive modeling in combustion chemistry, as it improves the accuracy of predictions and the reliability. To accurately predict ignition delay times and nitrogen oxides (NOx) emissions of ammonia (NH3) and hydrogen (H2) fuel blends, minimizi...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2025-01-01
|
| Series: | EPJ Web of Conferences |
| Online Access: | https://www.epj-conferences.org/articles/epjconf/pdf/2025/08/epjconf_cim2025_05002.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850185055410847744 |
|---|---|
| author | Wang Guanyu Wang Fan Jones Michael Nadiri Solmaz |
| author_facet | Wang Guanyu Wang Fan Jones Michael Nadiri Solmaz |
| author_sort | Wang Guanyu |
| collection | DOAJ |
| description | Uncertainty quantification (UQ) plays a crucial role in predictive modeling in combustion chemistry, as it improves the accuracy of predictions and the reliability. To accurately predict ignition delay times and nitrogen oxides (NOx) emissions of ammonia (NH3) and hydrogen (H2) fuel blends, minimizing uncertainty in combustion kinetic models is critical. This study introduces a novel approach that integrates Bayesian analysis with Artificial Neural Networks (ANNs) to perform inverse UQ and update combustion kinetic models based on experimentally measured nitric oxide (NO) speciation time history. Traditional Markov Chain Monte Carlo (MCMC) methods are effective, but they are computationally intensive and require large datasets, which limit their practical applicability. ANNs are applied as surrogate models to replace traditional kinetic modeling, optimizing the combustion kinetic model of NH3/H2 fuel blends. By integrating Bayesian analysis with ANNs, the computational cost was significantly reduced compared to conventional MCMC methods, while maintaining high accuracy in uncertainty quantification and parameter optimization. This approach facilitates efficient exploration of parameter space and ensures reliable predictions, making it a valuable tool for complex combustion modeling. |
| format | Article |
| id | doaj-art-fd34daf374bf4ab8a4c5fb5a64ba8ca8 |
| institution | OA Journals |
| issn | 2100-014X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | EPJ Web of Conferences |
| spelling | doaj-art-fd34daf374bf4ab8a4c5fb5a64ba8ca82025-08-20T02:16:50ZengEDP SciencesEPJ Web of Conferences2100-014X2025-01-013230500210.1051/epjconf/202532305002epjconf_cim2025_05002Bayesian Analysis of Combustion Kinetic Models for Ammonia-Hydrogen Fuel Blends Using Artificial Neural NetworksWang Guanyu0Wang Fan1Jones Michael2Nadiri Solmaz3Department of Physical Chemistry, Physikalisch-Technische BundesanstaltFaculty of Mathematics, Otto-von-Guericke-University MagdeburgQueen’s University KingstonDepartment of Physical Chemistry, Physikalisch-Technische BundesanstaltUncertainty quantification (UQ) plays a crucial role in predictive modeling in combustion chemistry, as it improves the accuracy of predictions and the reliability. To accurately predict ignition delay times and nitrogen oxides (NOx) emissions of ammonia (NH3) and hydrogen (H2) fuel blends, minimizing uncertainty in combustion kinetic models is critical. This study introduces a novel approach that integrates Bayesian analysis with Artificial Neural Networks (ANNs) to perform inverse UQ and update combustion kinetic models based on experimentally measured nitric oxide (NO) speciation time history. Traditional Markov Chain Monte Carlo (MCMC) methods are effective, but they are computationally intensive and require large datasets, which limit their practical applicability. ANNs are applied as surrogate models to replace traditional kinetic modeling, optimizing the combustion kinetic model of NH3/H2 fuel blends. By integrating Bayesian analysis with ANNs, the computational cost was significantly reduced compared to conventional MCMC methods, while maintaining high accuracy in uncertainty quantification and parameter optimization. This approach facilitates efficient exploration of parameter space and ensures reliable predictions, making it a valuable tool for complex combustion modeling.https://www.epj-conferences.org/articles/epjconf/pdf/2025/08/epjconf_cim2025_05002.pdf |
| spellingShingle | Wang Guanyu Wang Fan Jones Michael Nadiri Solmaz Bayesian Analysis of Combustion Kinetic Models for Ammonia-Hydrogen Fuel Blends Using Artificial Neural Networks EPJ Web of Conferences |
| title | Bayesian Analysis of Combustion Kinetic Models for Ammonia-Hydrogen Fuel Blends Using Artificial Neural Networks |
| title_full | Bayesian Analysis of Combustion Kinetic Models for Ammonia-Hydrogen Fuel Blends Using Artificial Neural Networks |
| title_fullStr | Bayesian Analysis of Combustion Kinetic Models for Ammonia-Hydrogen Fuel Blends Using Artificial Neural Networks |
| title_full_unstemmed | Bayesian Analysis of Combustion Kinetic Models for Ammonia-Hydrogen Fuel Blends Using Artificial Neural Networks |
| title_short | Bayesian Analysis of Combustion Kinetic Models for Ammonia-Hydrogen Fuel Blends Using Artificial Neural Networks |
| title_sort | bayesian analysis of combustion kinetic models for ammonia hydrogen fuel blends using artificial neural networks |
| url | https://www.epj-conferences.org/articles/epjconf/pdf/2025/08/epjconf_cim2025_05002.pdf |
| work_keys_str_mv | AT wangguanyu bayesiananalysisofcombustionkineticmodelsforammoniahydrogenfuelblendsusingartificialneuralnetworks AT wangfan bayesiananalysisofcombustionkineticmodelsforammoniahydrogenfuelblendsusingartificialneuralnetworks AT jonesmichael bayesiananalysisofcombustionkineticmodelsforammoniahydrogenfuelblendsusingartificialneuralnetworks AT nadirisolmaz bayesiananalysisofcombustionkineticmodelsforammoniahydrogenfuelblendsusingartificialneuralnetworks |