publications

Journal Articles

2025

1. AIAA J

   Rapid aerodynamic prediction of swept wings via physics-embedded transfer learning

   Yunjia Yang, Runze Li, Yufei Zhang, and 2 more authors

   AIAA Journal, Jun 2025

   Abs DOI

   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.

2024

1. A Fast Prediction Model of Supercritical Airfoils Based on Deep Operator Network and Variational Autoencoder Considering Physical Constraints

   Mengxin Liu, Yunjia Yang, Chenyu Wu, and 1 more author

   Aerospace Research Communications, Dec 2024

   Abs DOI

   Flow field prediction is crucial for evaluating the performance of airfoils and aerodynamic optimization. Computational fluid dynamics (CFD) methods usually require a considerable amount of computational resources and time. In this study, a composite model based on deep learning is proposed for flow field prediction. The variational autoencoder (VAE) model is designed to extract representative features of flow fields. The VAE model is trained to determine the optimal latent variable dimension and Kullback-Leibler (KL) divergence weight. Several physical constraints based on mass conservation and pressure coefficient are introduced to reduce the reconstruction loss and improve the model generalization ability. A DeepONet-MLP model, which combines a deep operator network (DeepONet) and a multilayer perceptron (MLP), is trained to achieve the nonlinear mapping from airfoil shapes and lift coefficients to latent variables in the VAE with fewer parameters. Eventually, a DeepONet-MLP-VAE model, which connects the decoder in VAE with DeepONet-MLP, is applied for fast flow field prediction. The results show that the proposed model can accurately and efficiently predict the transonic flow field, with a mean absolute error of 0.0016 and an average processing time of 0.010 s per flow field, which significantly accelerates the CFD evaluation process.

2. AIAA J

   Fast Buffet-Onset Prediction and Optimization Method Based on Pretrained Flowfield Prediction Model

   Yunjia Yang, Runze Li, Yufei Zhang, and 1 more author

   AIAA Journal, Aug 2024

   Abs DOI

   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.

3. PoF

   Transferable machine learning model for the aerodynamic prediction of swept wings

   Yunjia Yang, Runze Li, Yufei Zhang, and 2 more authors

   Physics of Fluids, Jul 2024

   Abs DOI

   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.

2023

1. AST

   Analysis and manipulation of the separation zone in an overexpanded combined exhaust nozzle

   Yunjia Yang, Yufei Zhang, and Haixin Chen

   Aerospace Science and Technology, Apr 2023

   DOI

2022

1. AIAA J

   Flowfield Prediction of Airfoil Off-Design Conditions Based on a Modified Variational Autoencoder

   Yunjia Yang, Runze Li, Yufei Zhang, and 1 more author

   AIAA Journal, Oct 2022

   DOI
2. 基于流体网络法的喷管冷却气流量分配计算方法

   杨韫加, 陈海昕, and 许羚

   航空动力学报, Jun 2022

   in Chinese

   Abs DOI

   流体网络法对喷管气膜冷却问题具有独特的优势，但难以反映出入流对冷却气流道静压变化的影响。针对此引入了可反映出入流导致静压变化的管道元件，并基于孔口速度落后角对静压变化量进行了建模。验证算例表明，这一改进使沿程静压变化趋势与实际吻合较好，使冷却气流量分配计算误差降低到0.5%以下。将改进后的流体网络法与主流通道的计算流体力学模拟耦合用于分析喷管冷却气流量分配，与全计算流体力学模拟相比结果差异小于1.2%，且大幅降低计算量；在某型喷管设计中的应用表明，可以有效反映冷却结构改变对冷却气流量分配的影响。

Conference Articles

2025

1. EUCASS

   Rapid aerodynamic prediction for wings via physics-embedded Transformer

   Yunjia Yang, Weishao Tang, Yufei Zhang, and 1 more author

   In 11th European Conference for AeroSpace Sciences (EUCASS). This paper is nominated as the top 3 best papers in the AEROFLIPHY + CFDMPS + FLOCON regions , Jul 2025

   Abs DOI

   Fast and accurate prediction of aerodynamic flow fields is essential for efficient aircraft design but remains challenging for complex transonic wing configurations. This study advances the use of machine learning for aerodynamic modeling by developing a generalizable dataset and applying Transformer-based neural network architectures to realistic wing geometries. A comprehensive dataset of transonic swept wings is constructed using a geometric parameterization approach inspired by engineering needs, covering a wide range of wing shapes and operating conditions. Two Transformer-based models are then investigated: the Vision Transformer (ViT) and the Physics-embedded Transformer (PeT), which incorporates physics-aware tokenization and attention mechanisms. The models are trained on the proposed dataset, and results show that Transformer-based models significantly outperform a U-Net baseline in predicting surface pressure and friction distributions, as well as integrated aerodynamic coefficients. The model implementations and an interactive prediction tool are released at https://github.com/YangYunjia/flogen, supporting future applications in data-driven aerodynamic design workflows.

2024

1. AIAA SCITECH

   Buffet onset optimization for supercritical airfoils with prior-based pressure profile prediction model

   Yunjia Yang, Runze Li, Yufei Zhang, and 1 more author

   In AIAA SCITECH 2024 Forum, Jan 2024

   DOI

2023

1. EUCASS

   Interactive optimization of fluidic injection for single expansion ramp nozzle based on a modified autoencoder

   Yunjia Yang, Jiazhe Li, Runze Li, and 2 more authors

   In Aerospace Europe Conference 2023 – 10ᵀᴴ EUCASS – 9ᵀᴴ CEAS, Jul 2023

   Abs DOI

   The single expansion ramp nozzle often experiences poor thrust performance at overexpansion conditions. Fluidic injection presents a promising solution to mitigate this issue, although there lacks an effective method to determine injection parameters under varying nozzle operating conditions. This paper presents a novel residual autoencoder surrogate model to fast calculate the pressure and temperature profiles on nozzle surfaces. Considering the characteristics of the nozzle flowfield, the model is designed to predict the difference between the profiles with and without the injection. This approach boosts the model’s predictive accuracy by 20% and enhances its transferability. Furthermore, the gradient-based optimization algorithm is applied to the model to discern optimal injection parameters under eleven distinct nozzle operating conditions whose nozzle pressure ratios range from 12 to 40. The results indicate a successful increase in average thrust coefficients by 0.76%, demonstrating the effectiveness of the proposed approach.

preprint

2024

1. Machine-learning-based multipoint optimization of fluidic injection parameters for improving nozzle performance

   Yunjia Yang, Jiazhe Li, Yufei Zhang, and 1 more author

   Jul 2024

   Abs HTML

   Fluidic injection provides a promising solution to improve the performance of overexpanded single expansion ramp nozzle (SERN) during vehicle acceleration. However, determining the injection parameters for the best overall performance under multiple nozzle operating conditions is still a challenge. The gradient-based optimization method requires gradients of injection parameters at each design point, leading to high computational costs if traditional computational fluid dynamic (CFD) simulations are adopted. This paper uses a pretrained neural network model to replace CFD during optimization to quickly calculate the nozzle flow field at multiple design points. Considering the physical characteristics of the nozzle flow field, a prior-based prediction strategy is adopted to enhance the model’s transferability. In addition, the back-propagation algorithm of the neural network is adopted to quickly evaluate the gradients by calling the computation process only once, thereby greatly reducing the gradient computation time compared to the finite differential method. As a test case, the average nozzle thrust coefficient of a SERN at seven design points is optimized. An improvement in the thrust coefficient of 1.14% is achieved, and the time cost is greatly reduced compared with the traditional optimization methods, even when the time to establish the database for training is considered.