A note on the improvement of Artificial Neural Network models for detonation cell size and critical tube diameter prediction
Bibliographic record
Abstract
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 Δ I . 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 D C . 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. • Prediction of detonation dynamic parameters in different gas mixtures based on ANN. • Improvement on the ANN formulation using non-dimensional input features. • The dropout technique is implemented to assess the uncertainty of the prediction. • A series of ANN- λ and ANN- D c models are built and tested for accuracy.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".