What is it about?
Turbine cooling is an effective way to improve the comprehensive performance and service life of gas turbines. In recent decades, there has been rapid growth in research into external cooling and internal cooling methods. As a result, there is a significant amount of experimental and numerical data. However, due to their multi-source nature, the datasets have different degrees of fidelity and different data structures, which hinders the effective use of the data. Besides, high-fidelity data often have high acquisition costs, which hinders their application in aerospace. A novel form of data fusion is introduced in this paper. We integrate multi-source data using special algorithms to produce more reliable data. A deep-learning neural network with the PointNet architecture is designed to establish two surrogate models: a high-fidelity model (HF model) trained by experimental data and a low-fidelity model (LF model) based on Reynolds-averaged Navier--Stokes simulation data. Both models predict results with less than 1% reference errors compared to their respective ground truth at most data points. In addition, we explore the role of transfer learning in multi-fidelity modeling. A fusion algorithm based on a Gaussian function and a weighted average strategy is proposed to combine the values from the HF model and the LF model. The presented results show that the fusion data are more accurate than computational fluid dynamics data, successfully meeting the goal of reducing the cost of data acquisition.
Featured Image
Photo by Luka Slapnicar on Unsplash
Why is it important?
With the continuous development of computational and experimental tools, we have been able to accumulate considerable data on turbine blade cooling design. Abundant data often comes with complex data structures and varying data precision, which hinders the full use of them. In order to advance the digital and intelligent process of the turbine design system, new methods need to be proposed. Our work is a step in that direction.
Perspectives
Our results demonstrate that PointNet-based data fusion methods have higher prediction fidelity, with higher computational efficiency and less time cost. Of course, there are still some inadequacies in the existing work, and more appropriate fusion algorithms are still to be explored
Zuobiao Li
Harbin Institute of Technology
Based on the data with different fidelity of numerical simulation and test, we conducted data fusion to predict the surface temperature of a turbine blade with complex geometry, which is of great significance and can provide a good reference for multi-source data fusion for digital twins
Fengbo Wen
Harbin Institute of Technology
Read the Original
This page is a summary of: Cost reduction for data acquisition based on data fusion: Reconstructing the surface temperature of a turbine blade, Physics of Fluids, January 2023, American Institute of Physics,
DOI: 10.1063/5.0132105.
You can read the full text:
Contributors
The following have contributed to this page
