A No-Calibration Approach to Modelling Compressor Blade Rows With Body Forces Employing Artificial Neural Networks
Bibliographic record
Abstract
Abstract Body force modelling in numerical simulations of axial compressors and fans has been used extensively in the literature to assess aerodynamic performance in uniform and non-uniform flow at relatively low computational cost. Existing approaches require calibration or, in the case of purely analytical models, are unable to accurately predict losses. It can also be challenging to capture the chordwise loading distribution with existing analytical models. This paper introduces a new body force modelling approach in which blade loading is computed using an isolated-airfoil, analytical model supplemented by a trained artificial-neural-network-based correction factor for finite pitch effects. The loading model is derived from potential flow theory and accounts for both camber and thickness effects; it captures both the overall and local loading. The approach is currently implemented for low-Mach number (incompressible) flows. The body forces causing flow turning derive directly from the corrected loading model. Forces arising from viscous losses are modeled by solving the integral boundary layer equations along streamlines within blade rows based on the fictitious edge velocities computed by the loading model. The viscous loss force is a function of the local dissipation coefficients. The approach is implemented within a traditional finite-volume computational fluid dynamics solver. In this paper, the application is limited to 2D cascades. To assess the approach, results from the body force model are compared to blade-to-blade solutions from MISES. The key findings are (1) that a relatively modest set of training data for the neural network produces a robust finite pitch correction, and (2) that the modelling approach is able to successfully capture the flow turning and losses associated with a variety of low-speed compressor cascades without any calibration specific to the blade row(s) being modeled.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".