Shape optimization of impingement and film cooling holes on a flat plate using a feedforward ANN and GA
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Numerical simulations of a three-dimensional model of impingement and film cooling on a flat plate are presented and validated with the available experimental data. Four different turbulence models were utilized for simulation, in which SST had the highest precision, resulting in less than 4% maximum error in temperature estimation. A simplified geometry with periodic boundary conditions is designed, based on the main geometry, and is used for the optimization procedure. Six geometrical parameters related to impingement and film holes are selected as design variables. To further reduce the time required for optimization, a feedforward neural network is implemented for the function estimation, and 584 CFD observations were performed for randomly generated design points. The data from CFD simulations were fed to network for training and test operations, and the results with good consistency were extracted from the network. The objective of the optimization is to minimize the coolant mass flow rate, subject to maximum temperature and maximum temperature gradient in solid domain being equal to or lower than their values in base design. A genetic algorithm (GA) with 100 population and 50 iterations, coupled with an artificial neural network (ANN), was used for optimization. Finally, the optimum design is simulated numerically to find the exact values of the output parameters. The CFD results for optimum design shows 44% less coolant mass flow rate while both optimization constraints are satisfied. Such a reduction in the coolant flow rate has a huge impact on the overall performance of a typical gas turbine, which is discussed in this paper.
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.
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 | 0.000 |
| 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 it