Journal of Chinese Society of Power Engineering
|
2026, 46(1): 51-58
A Parametric Kernel Model to Predict Film Effectiveness of Fan-shaped Holes
Full
Affiliations
Published: 2026-01-15
doi: 10.19805/j.cnki.jcspe.2026.250282
Outline
In the calculation of a regional film cooling effectiveness covered by arrayed discrete holes, conventional computational fluid dynamics (CFD) simulations are confronted with the challenges of complex grid modeling and high computation consumption. A parameterized kernel function was proposed to describe the distribution characteristics of a single fan-shaped hole and then to predict the film cooling efficiency. Integrating data-driven machine learning technique with the Sellers film cooling efficiency superposition method, the efficient prediction of cooling efficiency distribution in the coverage area of group holes was realized. Based on the parametric "Kernel" model, the cooling effectiveness distribution for both single and triple in-line rows of 7-7-7 fan-shaped holes were successfully replicated. Furthermore, In the given region, the layout of in-line group holes with the highest average cooling efficiency in the region was obtained with integer programming method. Results show that the parametric "Kernel" model can accurately reflect the distribution characteristics of cooling efficiency in the film hole coverage area, overcoming the limitation of traditional correlation equations that only predict spanwise average cooling efficiency, and significantly reduce the number of samples required for machine learning, which can be applied to the prediction of film cooling efficiency under different working conditions.
film cooling
/
Gaussian kernel
/
artificial neural network
/
full coverage prediction
.
预测扇形孔气膜分布的“核”参数模型.
动力工程学报,
2026
, 46
(1)
: 51
-58
.
DOI: 10.19805/j.cnki.jcspe.2026.250282
.
A Parametric Kernel Model to Predict Film Effectiveness of Fan-shaped Holes[J].
Journal of Chinese Society of Power Engineering,
2026
, 46
(1)
: 51
-58
.
DOI: 10.19805/j.cnki.jcspe.2026.250282
Year 2026 volume 46 Issue 1
71
16
Cite this Article
BibTeX
Article Info
doi: 10.19805/j.cnki.jcspe.2026.250282
- Receive Date:2025-05-20
- Online Date:2026-11-05
- Published:2026-01-15