Purpose

To improve the speed and accuracy of turbine blade film cooling design process, the most advanced deep learning models were introduced into this study to investigate the most suitable define for prediction work. This paper aims to create a generative surrogate model that can be applied on multi-objective optimization problems.

Design/methodology/approach

The latest backbone in the field of computer vision (Swin-Transformer, 2021) was introduced and improved as the surrogate function for prediction of the multi-physics field distribution (film cooling effectiveness, pressure, density and velocity). The basic samples were generated by Latin hypercube sampling method and the numerical method adopt for the calculation was validated experimentally at first. The training and testing samples were calculated at experimental conditions. At last, the surrogate model predicted results were verified by experiment in a linear cascade.

Findings

The results indicated that comparing with the Multi-Scale Pix2Pix Model, the Swin-Transformer U-Net model presented higher accuracy and computing speed on the prediction of contour results. The computation time for each step of the Swin-Transformer U-Net model is one-third of the original model, especially in the case of multi-physics field prediction. The correlation index reached more than 99.2% and the first-order error was lower than 0.3% for multi-physics field. The predictions of the data-driven surrogate model are consistent with the predictions of the computational fluid dynamics results, and both are very close to the experimental results. The application of the Swin-Transformer model on enlarging the different structure samples will reduce the cost of numerical calculations as well as experiments.

Research limitations/implications

The number of U-Net layers and sample scales has a proper relationship according to equation (8). Too many layers of U-Net will lead to unnecessary nonlinear variation, whereas too few layers will lead to insufficient feature extraction. In the case of Swin-Transformer U-Net model, incorrect number of U-Net layer will reduce the prediction accuracy. The multi-scale Pix2Pix model owns higher accuracy in predicting a single physical field, but the calculation speed is too slow. The Swin-Transformer model is fast in prediction and training (nearly three times faster than multi Pix2Pix model), but the predicted contours have more noise. The neural network predicted results and numerical calculations are consistent with the experimental distribution.

Originality/value

This paper creates a generative surrogate model that can be applied on multi-objective optimization problems. The generative adversarial networks using new backbone is chosen to adjust the output from single contour to multi-physics fields, which will generate more results simultaneously than traditional surrogate models and reduce the time-cost. And it is more applicable to multi-objective spatial optimization algorithms. The Swin-Transformer surrogate model is three times faster to computation speed than the Multi Pix2Pix model. In the prediction results of multi-physics fields, the prediction results of the Swin-Transformer model are more accurate.

中文翻译：

---

使用具有各种深度学习框架的优化代理模型来预测燃气轮机端壁上的多物理场分布

目的

为了提高涡轮叶片气膜冷却设计过程的速度和准确性，本研究引入了最先进的深度学习模型，以研究最适合预测工作的定义。本文旨在创建一个可应用于多目标优化问题的生成代理模型。

设计/方法论/途径

引入并改进了计算机视觉领域的最新主干（Swin-Transformer，2021）作为预测多物理场分布（薄膜冷却效率、压力、密度和速度）的代理函数。采用拉丁超立方采样法生成基本样本，并首先对计算所采用的数值方法进行了实验验证。训练和测试样本是在实验条件下计算的。最后，通过线性级联实验验证了代理模型的预测结果。

发现

结果表明，与多尺度Pix2Pix模型相比，Swin-Transformer U-Net模型在轮廓结果预测上表现出更高的精度和计算速度。Swin-Transformer U-Net模型每一步的计算时间是原始模型的三分之一，特别是在多物理场预测的情况下。多物理场相关性指数达到99.2%以上，一阶误差低于0.3%。数据驱动代理模型的预测与计算流体力学结果的预测一致，并且都与实验结果非常接近。应用Swin-Transformer模型放大不同结构的样本将降低数值计算和实验的成本。

研究局限性/影响

U-Net层数和样本尺度根据式（8）有适当的关系。U-Net的层数过多会导致不必要的非线性变化，而层数过少又会导致特征提取不足。对于Swin-Transformer U-Net模型，错误的U-Net层数会降低预测精度。多尺度Pix2Pix模型对单一物理场的预测精度较高，但计算速度较慢。Swin-Transformer模型的预测和训练速度很快（比多Pix2Pix模型快近三倍），但预测的轮廓有更多的噪声。神经网络预测结果和数值计算结果与实验分布一致。

原创性/价值

本文创建了一个可应用于多目标优化问题的生成代理模型。选择使用新主干的生成对抗网络将输出从单一轮廓调整为多物理场，这将比传统代理模型同时生成更多结果并减少时间成本。并且更适用于多目标空间优化算法。Swin-Transformer 代理模型的计算速度比 Multi Pix2Pix 模型快三倍。在多物理场的预测结果中，Swin-Transformer模型的预测结果更加准确。