Artificial Neural Networks Prediction of Wall-Pressure Spectrum
Bibliographic record
Abstract
An alternative to semi-empirical models of wall-pressure spectra beneath turbulent boundary layers (TBL) based on machine learning is presented in this work. To do so, Artificial Neural Networks (ANN) have been employed, as they have already been proven to work for this type of prediction. The previous efforts have been based on finding relationships between the boundary layer and the wall-pressure spectrum (WPS), always using a set of predefined features that drive the BL behavior. In this work, the complete boundary layer velocity profile is used to obtain the WPS prediction. The machine learning algorithm is composed of two separated ANNs: a velocity autoencoder to compress and extract the minimum required parameters driving the boundary layer, and a WPS predictor. The training and analysis of the ANN are performed on LES and DNS numerical data, covering a wide range of flow conditions. The results on the exploitation of the database have resulted in the evidence of the existence of a minimum of three boundary layer parameters driving the boundary layer evolution, no matter the nature of the pressure gradient (forward, zero, or adverse). The WPS prediction produces a global –in position and frequency– mean error of 3.2 dB/Hz, and it captures the effect of the main mid-frequency tonal peak as well as the generalized noise trends in the low, mid, and high-frequency content.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".