Fast prediction and uncertainty analysis of film cooling with a semi-sphere vortex generator using artificial neural network

Wang, Yaning; Qian, Shuyang; Sun, Yangqing; Wen, Wang; Cui, Jiahuan

doi:10.1063/5.0132989

Cited by 3 publications

(1 citation statement)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is deduced that it is accessible to use deep learning methods in film cooling research. Furthermore, Wang et al also applied a supervised ANN on a SVG cooling configuration to explore the non-linear mapping between parameters and performance and conclude that when the blowing ratio is low, the radius of SVG dominates the cooling effectiveness (23).…”

Section: Introductionmentioning

confidence: 99%

Deep‐Learning-Based Uncertainty Analysis of Flat Plate Film Cooling With Application to Gas Turbine

Wang

Qiu

Qian

et al. 2023

Aerosp. Res. Commun.

Self Cite

View full text Add to dashboard Cite

Nowadays, gas turbines intake jet air at high temperatures to improve the power output as much as possible. However, the excessive temperature typically puts the blade in the face of unpredictable damage. Film cooling is one of the prevailing methods applied in engineering scenarios, with the advantages of a simple structure and high cooling efficiency. This study aims to assess the uncertain effect that the three major film cooling parameters exert on the global and fixed-cord-averaged film cooling effectiveness under low, medium, and high blowing ratios br. The three input parameters include coolant hole diameter d, coolant tube inclination angle θ, and density ratio dr. The training dataset is obtained by Computational Fluid Dynamics (CFD). Moreover, a seven-layer artificial neural network (ANN) algorithm is applied to explore the complex non-linear mapping between the input flat film cooling parameters and the output fixed-cord-averaged film cooling effectiveness on the external turbine blade surface. The sensitivity experiment conducted using Monte Carlo (MC) simulation shows that the d and θ are the two most sensitive parameters in the low-blowing-ratio cases. The θ comes to be the only leading factor of sensitivity in larger blowing ratio cases. As the blowing ratio rises, the uncertainty of the three parameters d, θ, and dr all decrease. The combined effect of the three parameters is also dissected and shows that it has a more significant influence on the general cooling effectiveness than any single effect. The d has the widest variation of uncertainty interval at three blowing ratios, while the θ has the largest uncertain influence on the general cooling effectiveness. With the aforementioned results, the cooling effectiveness of the gas turbine can be furthermore enhanced.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep‐Learning-Based Uncertainty Analysis of Flat Plate Film Cooling With Application to Gas Turbine

Wang

Qiu

Qian

et al. 2023

Aerosp. Res. Commun.

Self Cite

View full text Add to dashboard Cite

show abstract

Fluid flow and heat transfer characteristics of three-dimensional slot film cooling in an annular combustor

Revulagadda

Adapa

Balaji

et al. 2023

International Journal of Heat and Mass Transfer

View full text Add to dashboard Cite

Enhancing generalization in endwall film cooling prediction: Incorporating the superposition principle into transformer-based neural operators

Wang,

Song,

Liu

et al. 2024

Physics of Fluids

View full text Add to dashboard Cite

In this study, a physics-enhanced neural operator framework is proposed to enhance the generalization prediction ability of the cooling layout of a turbine end wall with variable number of film holes. Specifically, inspired by the film cooling superposition principle, the superposition-based deep neural operator (SDNO) network is proposed, which divides the turbine end wall's temperature field prediction into two stages. In the first stage, the cooling layout of a turbine end wall is divided into several sub-parts, and a transformer-based neural operator network, namely Calculate Net, is designed to predict the temperature field of each sub-part. Then, in the second stage, another neural operator network, i.e., Superposition Net, is designed to combine all the temperature fields of each sub-part and obtain the final superposed field of full cooling layout. Additionally, instead of directly taking the film cooling layout as binary pixel data, a signed distance function which is sensitive to the variable locations of cooling holes is designed to preprocess the input layout information. Furthermore, the proposed end wall film cooling prediction model is trained with samples varying the number of film holes from 1 to 5 at different locations. Then, the trained prediction shows excellent generalization prediction ability, which can accurately predict the film effectiveness of the cooling layout with 10–20 film cooling holes that are unseen in the training samples. In the meantime, the proposed SDNO network also shows remarkable better prediction accuracy. With the above, the effectiveness of the SDNO has been well demonstrated.

show abstract

Fast prediction and uncertainty analysis of film cooling with a semi-sphere vortex generator using artificial neural network

Cited by 3 publications

References 49 publications

Deep‐Learning-Based Uncertainty Analysis of Flat Plate Film Cooling With Application to Gas Turbine

Deep‐Learning-Based Uncertainty Analysis of Flat Plate Film Cooling With Application to Gas Turbine

Fluid flow and heat transfer characteristics of three-dimensional slot film cooling in an annular combustor

Enhancing generalization in endwall film cooling prediction: Incorporating the superposition principle into transformer-based neural operators

Contact Info

Product

Resources

About