A note on the improvement of Artificial Neural Network models for detonation cell size and critical tube diameter prediction
In this note we present strategies to improve a deep Artificial Neural Network (ANN) to predict the dynamic parameters of gaseous detonations in hydrogen- and other hydrocarbon-based mixtures. These new strategies involve using only non-dimensional features for the model, which have been created usi...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-12-01
|
| Series: | Nuclear Engineering and Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1738573325003924 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849240663501045760 |
|---|---|
| author | Georgios Bakalis Yifan Lyu Hoi Dick Ng |
| author_facet | Georgios Bakalis Yifan Lyu Hoi Dick Ng |
| author_sort | Georgios Bakalis |
| collection | DOAJ |
| description | In this note we present strategies to improve a deep Artificial Neural Network (ANN) to predict the dynamic parameters of gaseous detonations in hydrogen- and other hydrocarbon-based mixtures. These new strategies involve using only non-dimensional features for the model, which have been created using thermochemical and chemical kinetic parameters from the steady reaction zone structure commonly used in detonation studies, as well as a non-dimensional target, obtained by dividing the experimental cell size with the induction length ΔI. In addition, the ANN model's structure has been supplemented with dropout layers, thus improving the training process and also leading to a better determination of the model's uncertainty. Apart from predicting the detonation cell size, this updated model creation approach is implemented to the critical tube problem, combining thermochemical and kinetic parameters with experimental data to create an accurate model that predicts the critical tube diameter DC. The optimal structure and combination of features for the ANN are thoroughly assessed. The source codes of the ANN models are readily available on GitHub. |
| format | Article |
| id | doaj-art-c1c1fad8242b4ed3b2973ddf16a7d8b4 |
| institution | Kabale University |
| issn | 1738-5733 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Nuclear Engineering and Technology |
| spelling | doaj-art-c1c1fad8242b4ed3b2973ddf16a7d8b42025-08-20T04:00:28ZengElsevierNuclear Engineering and Technology1738-57332025-12-01571210382410.1016/j.net.2025.103824A note on the improvement of Artificial Neural Network models for detonation cell size and critical tube diameter predictionGeorgios Bakalis0Yifan Lyu1Hoi Dick Ng2Corresponding author. Department of Mechanical, Industrial and Aerospace Engineering Concordia University 1455 de Maisonneuve Blvd. West, Montreal, QC H3G 1M8 Canada.; Department of Mechanical, Industrial and Aerospace Engineering, Concordia University, Montreal, QC, H3G 1M8, CanadaDepartment of Mechanical, Industrial and Aerospace Engineering, Concordia University, Montreal, QC, H3G 1M8, CanadaDepartment of Mechanical, Industrial and Aerospace Engineering, Concordia University, Montreal, QC, H3G 1M8, CanadaIn this note we present strategies to improve a deep Artificial Neural Network (ANN) to predict the dynamic parameters of gaseous detonations in hydrogen- and other hydrocarbon-based mixtures. These new strategies involve using only non-dimensional features for the model, which have been created using thermochemical and chemical kinetic parameters from the steady reaction zone structure commonly used in detonation studies, as well as a non-dimensional target, obtained by dividing the experimental cell size with the induction length ΔI. In addition, the ANN model's structure has been supplemented with dropout layers, thus improving the training process and also leading to a better determination of the model's uncertainty. Apart from predicting the detonation cell size, this updated model creation approach is implemented to the critical tube problem, combining thermochemical and kinetic parameters with experimental data to create an accurate model that predicts the critical tube diameter DC. The optimal structure and combination of features for the ANN are thoroughly assessed. The source codes of the ANN models are readily available on GitHub.http://www.sciencedirect.com/science/article/pii/S1738573325003924Gaseous detonationArtificial Neural NetworksCell sizeCritical tube diameter |
| spellingShingle | Georgios Bakalis Yifan Lyu Hoi Dick Ng A note on the improvement of Artificial Neural Network models for detonation cell size and critical tube diameter prediction Nuclear Engineering and Technology Gaseous detonation Artificial Neural Networks Cell size Critical tube diameter |
| title | A note on the improvement of Artificial Neural Network models for detonation cell size and critical tube diameter prediction |
| title_full | A note on the improvement of Artificial Neural Network models for detonation cell size and critical tube diameter prediction |
| title_fullStr | A note on the improvement of Artificial Neural Network models for detonation cell size and critical tube diameter prediction |
| title_full_unstemmed | A note on the improvement of Artificial Neural Network models for detonation cell size and critical tube diameter prediction |
| title_short | A note on the improvement of Artificial Neural Network models for detonation cell size and critical tube diameter prediction |
| title_sort | note on the improvement of artificial neural network models for detonation cell size and critical tube diameter prediction |
| topic | Gaseous detonation Artificial Neural Networks Cell size Critical tube diameter |
| url | http://www.sciencedirect.com/science/article/pii/S1738573325003924 |
| work_keys_str_mv | AT georgiosbakalis anoteontheimprovementofartificialneuralnetworkmodelsfordetonationcellsizeandcriticaltubediameterprediction AT yifanlyu anoteontheimprovementofartificialneuralnetworkmodelsfordetonationcellsizeandcriticaltubediameterprediction AT hoidickng anoteontheimprovementofartificialneuralnetworkmodelsfordetonationcellsizeandcriticaltubediameterprediction AT georgiosbakalis noteontheimprovementofartificialneuralnetworkmodelsfordetonationcellsizeandcriticaltubediameterprediction AT yifanlyu noteontheimprovementofartificialneuralnetworkmodelsfordetonationcellsizeandcriticaltubediameterprediction AT hoidickng noteontheimprovementofartificialneuralnetworkmodelsfordetonationcellsizeandcriticaltubediameterprediction |