Yunjia Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yunjia Yang has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Runze Li
School of Aerospace Engineering, Tsinghua University, Beijing 100084, China
3 shared publications Haixin Chen
Tsinghua University
2 shared publications- Haixin Chen
School of Aerospace Engineering, Tsinghua University, Beijing 100084, China
2 shared publications - Lu Lu
Department of Statistics and Data Science Yale University New Haven Connecticut USA
2 shared publications Yufei Zhang
Tsinghua University
2 shared publications- Yufei Zhang
Tsinghua University
2 shared publications
Latest Publications
- 14 August 2026
- Published by American Institute of Aeronautics and Astronautics (AIAA) in AIAA Journal
- p. 1-21
Toward a Foundation-Model Paradigm for Aerodynamic Prediction in Three-Dimensional Design
Accurate machine-learning models for aerodynamic prediction are essential for accelerating shape optimization yet remain challenging to develop for complex three-dimensional configurations due to the high cost of generating training data. This work introduces a methodology for efficiently constructing accurate surrogate models for design purposes by first pretraining a large-scale model on diverse geometries and then fine-tuning it with a few more detailed task-specific samples. A Transformer-based architecture, AeroTransformer, is developed and tailored for large-scale training to learn aerodynamics. The methodology is evaluated on transonic wings, where the model is pretrained on SuperWing, a dataset of nearly 30,000 samples with broad geometric diversity, and subsequently fine-tuned to handle specific wing shapes perturbed from the Common Research Model. Results show that, with 450 task-specific samples, the proposed methodology achieves a 0.36% error on surface-flow prediction, reducing error by 84.2% compared to training from scratch. The influence of model configurations and training strategies is also systematically studied to provide guidance on effectively training and deploying such models under limited data and computational budgets. To facilitate reuse, we release the datasets and the pretrained models at https://github.com/tum-pbs/AeroTransformer . An interactive design tool is also built on the pretrained model and is available online at https://webwing.pbs.cit.tum.de .
- 14 August 2026
- Published by American Institute of Aeronautics and Astronautics (AIAA) in AIAA Journal
- p. 1-21
Toward a Foundation-Model Paradigm for Aerodynamic Prediction in Three-Dimensional Design
Accurate machine-learning models for aerodynamic prediction are essential for accelerating shape optimization yet remain challenging to develop for complex three-dimensional configurations due to the high cost of generating training data. This work introduces a methodology for efficiently constructing accurate surrogate models for design purposes by first pretraining a large-scale model on diverse geometries and then fine-tuning it with a few more detailed task-specific samples. A Transformer-based architecture, AeroTransformer, is developed and tailored for large-scale training to learn aerodynamics. The methodology is evaluated on transonic wings, where the model is pretrained on SuperWing, a dataset of nearly 30,000 samples with broad geometric diversity, and subsequently fine-tuned to handle specific wing shapes perturbed from the Common Research Model. Results show that, with 450 task-specific samples, the proposed methodology achieves a 0.36% error on surface-flow prediction, reducing error by 84.2% compared to training from scratch. The influence of model configurations and training strategies is also systematically studied to provide guidance on effectively training and deploying such models under limited data and computational budgets. To facilitate reuse, we release the datasets and the pretrained models at https://github.com/tum-pbs/AeroTransformer . An interactive design tool is also built on the pretrained model and is available online at https://webwing.pbs.cit.tum.de .
- 1 June 2025
- Published by American Institute of Aeronautics and Astronautics (AIAA) in AIAA Journal
- Vol. 63 (6) , 2545-2559
Rapid Aerodynamic Prediction of Swept Wings via Physics-Embedded Transfer Learning
Machine-learning-based models provide a promising way to rapidly acquire transonic swept wing flow fields but suffer from large computational costs in establishing training datasets. Here, a physics-embedded transfer-learning framework is proposed to efficiently train the model by leveraging the idea that a three-dimensional flow field around wings can be analyzed with two-dimensional flow fields around cross-sectional airfoils. An airfoil aerodynamics prediction model is pretrained with airfoil samples. Then, an airfoil-to-wing transfer model is fine-tuned with a few wing samples to predict three-dimensional flow fields based on two-dimensional results on each spanwise cross section. Sweep theory is embedded when determining the corresponding airfoil geometry and operating conditions, and to obtain the sectional airfoil lift coefficient, which is one of the operating conditions, the low-fidelity vortex lattice method and data-driven methods are proposed and evaluated. Compared to a nontransfer model, introducing the pretrained model reduces the error by 30%, whereas introducing sweep theory further reduces the error by 9%. When reducing the dataset size, less than half of the wing training samples are need to reach the same error level as the nontransfer framework, which makes establishing the model much easier.
- 1 June 2025
- Published by American Institute of Aeronautics and Astronautics (AIAA) in AIAA Journal
- Vol. 63 (6) , 2545-2559
Rapid Aerodynamic Prediction of Swept Wings via Physics-Embedded Transfer Learning
Machine-learning-based models provide a promising way to rapidly acquire transonic swept wing flow fields but suffer from large computational costs in establishing training datasets. Here, a physics-embedded transfer-learning framework is proposed to efficiently train the model by leveraging the idea that a three-dimensional flow field around wings can be analyzed with two-dimensional flow fields around cross-sectional airfoils. An airfoil aerodynamics prediction model is pretrained with airfoil samples. Then, an airfoil-to-wing transfer model is fine-tuned with a few wing samples to predict three-dimensional flow fields based on two-dimensional results on each spanwise cross section. Sweep theory is embedded when determining the corresponding airfoil geometry and operating conditions, and to obtain the sectional airfoil lift coefficient, which is one of the operating conditions, the low-fidelity vortex lattice method and data-driven methods are proposed and evaluated. Compared to a nontransfer model, introducing the pretrained model reduces the error by 30%, whereas introducing sweep theory further reduces the error by 9%. When reducing the dataset size, less than half of the wing training samples are need to reach the same error level as the nontransfer framework, which makes establishing the model much easier.
- 1 July 2024
- Published by AIP Publishing in Physics of Fluids
- Vol. 36 (7)
Transferable machine learning model for the aerodynamic prediction of swept wings
With their development, machine learning models can be used instead of computational fluid dynamics simulations to predict flow fields in aerodynamic optimization. However, it is difficult to construct a prediction model for swept wings with various planform geometries because too many samples are required to cover the parameter space. In the present paper, a new model framework is proposed to predict wing surface pressure and friction distributions with fewer samples. The distributed geometry parameters along spanwise are used as model inputs instead of the global planform parameters, and processors are designed to help the model better learn the local effect of geometric variation. The model is trained and tested on simple swept wings with single segment and linear twist distribution, where it outperforms the global input model by 57.6% in terms of lift coefficient prediction errors on small dataset sizes. The distributed input also enables the model to be transferred from single wings to more engineering-practical yet complex kink wings. After fine-tuning with a few samples, model accuracy for kink wings can be similar to that of simple wings, which proves the model for wings with complex planform geometries can be efficiently built with the proposed method.
- 1 July 2024
- Published by AIP Publishing in Physics of Fluids
- Vol. 36 (7)
Transferable machine learning model for the aerodynamic prediction of swept wings
With their development, machine learning models can be used instead of computational fluid dynamics simulations to predict flow fields in aerodynamic optimization. However, it is difficult to construct a prediction model for swept wings with various planform geometries because too many samples are required to cover the parameter space. In the present paper, a new model framework is proposed to predict wing surface pressure and friction distributions with fewer samples. The distributed geometry parameters along spanwise are used as model inputs instead of the global planform parameters, and processors are designed to help the model better learn the local effect of geometric variation. The model is trained and tested on simple swept wings with single segment and linear twist distribution, where it outperforms the global input model by 57.6% in terms of lift coefficient prediction errors on small dataset sizes. The distributed input also enables the model to be transferred from single wings to more engineering-practical yet complex kink wings. After fine-tuning with a few samples, model accuracy for kink wings can be similar to that of simple wings, which proves the model for wings with complex planform geometries can be efficiently built with the proposed method.
- 12 May 2024
- Published by American Institute of Aeronautics and Astronautics (AIAA) in AIAA Journal
- Vol. 62 (8) , 1-17
Fast Buffet-Onset Prediction and Optimization Method Based on Pretrained Flowfield Prediction Model
A transonic buffet is a detrimental phenomenon that occurs on supercritical airfoils and limits the aircraft operating envelope. Traditional methods for predicting buffet onset rely on multiple computational fluid dynamics simulations to assess a series of airfoil flowfields and then apply criteria to them, which is slow and hinders optimization efforts. This study introduces an innovative approach for rapid buffet-onset prediction. A machine-learning flowfield prediction model was pretrained on a large database and then deployed offline to replace the simulations in the buffet prediction process for new airfoil designs. Unlike using a model to directly predict buffet onset, the proposed technique offers better visualization capabilities by providing users with intuitive flowfield outputs. It also demonstrates superior generalization ability, as evidenced by a 32.5% reduction in the average buffet-onset prediction error on the testing dataset. This method was used to optimize the buffet performance of 11 distinct airfoils within and outside the training dataset. The optimization results were verified with simulations and proved to yield improved samples across all cases. It was affirmed that the pretrained flowfield prediction model can be applied to accelerate aerodynamic shape optimization, but further work is still needed to raise its reliability for this safety-critical task.
- 12 May 2024
- Published by American Institute of Aeronautics and Astronautics (AIAA) in AIAA Journal
- Vol. 62 (8) , 1-17
Fast Buffet-Onset Prediction and Optimization Method Based on Pretrained Flowfield Prediction Model
A transonic buffet is a detrimental phenomenon that occurs on supercritical airfoils and limits the aircraft operating envelope. Traditional methods for predicting buffet onset rely on multiple computational fluid dynamics simulations to assess a series of airfoil flowfields and then apply criteria to them, which is slow and hinders optimization efforts. This study introduces an innovative approach for rapid buffet-onset prediction. A machine-learning flowfield prediction model was pretrained on a large database and then deployed offline to replace the simulations in the buffet prediction process for new airfoil designs. Unlike using a model to directly predict buffet onset, the proposed technique offers better visualization capabilities by providing users with intuitive flowfield outputs. It also demonstrates superior generalization ability, as evidenced by a 32.5% reduction in the average buffet-onset prediction error on the testing dataset. This method was used to optimize the buffet performance of 11 distinct airfoils within and outside the training dataset. The optimization results were verified with simulations and proved to yield improved samples across all cases. It was affirmed that the pretrained flowfield prediction model can be applied to accelerate aerodynamic shape optimization, but further work is still needed to raise its reliability for this safety-critical task.
- 20 February 2023
- Published by Elsevier in Aerospace Science and Technology
- Vol. 135
Analysis and manipulation of the separation zone in an overexpanded combined exhaust nozzle
- 20 February 2023
- Published by Elsevier in Aerospace Science and Technology
- Vol. 135
Analysis and manipulation of the separation zone in an overexpanded combined exhaust nozzle