Jianmiao Yi

Mr. Jianmiao Yi


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 January 2023 in Aerospace
Verified
Journal Article
Open access
PDF file
Feng DengFeng Deng
Feng Deng
JYJianmiao Yi
Jianmiao Yi
In this paper, a deep learning model trained to generate well-posed pressure distributions at transonic speeds is coupled by the efficient global optimization (EGO) algorithm to speed up the inverse design process for transonic airfoils. First, the Wasserstein generative adversarial network (WGAN) is trained to generate well-posed pressure distributions at transonic speeds. Then, the EGO algorithm is used to pick up a pressure distribution in WGAN by solving the associated optimization problem defined for matching the prescribed pressure features, such as the suction peak and the shock-wave position. Finally, a deep convolutional neural network (DCNN) for nonlinear mapping is adopted to obtain the corresponding airfoil shape. Several cases with prescribed pressure features were performed to verify the feasibility and efficiency of the proposed method. Test cases indicate that the airfoil shape with the desired pressure distribution can be found in around one minute using a desktop computer with an Intel i5-9300H CPU.

20 July 2023 in Aerospace
Verified
Journal Article
Open access
PDF file
JYJianmiao Yi
Jianmiao Yi
Feng DengFeng Deng
Feng Deng
An airfoil shape parameterization that can generate a compact design space is highly desirable in practice. In this paper, a compact airfoil parameterization is proposed by incorporating deep learning into the PAERO parameterization method based on the thin-airfoil theory. Following the PAERO parameterization, the mean camber line is represented by a number of aerodynamic performance parameters, which can be used to narrow down the design space according to the thin-airfoil theory. In order to further reduce the design space, the airfoil thickness distribution is represented by data-driven generative models, which are trained by the thickness distributions of existing airfoils. The trained models can automatically filter out the physically unreasonable airfoil shapes, resulting in a highly compact design space. The test results show that the proposed method is significantly more efficient and more robust than the widely used CST parameterization method for airfoil optimization.

10 June 2026 in Aerospace
Verified
Journal Article
Open access
PDF file
Feng DengFeng Deng
Feng Deng
JYJianmiao Yi
Jianmiao Yi
GCGuanhua Chen
Guanhua Chen
Ning QinNing Qin
Ning Qin
This paper presents the design of shock control bumps on a double-fuselage aircraft with a natural laminar flow (NLF) wing section. Both two-dimensional (2D) and three-dimensional (3D) bumps were investigated to identify the high-impact factors on both shock control and natural laminar flow for the aircraft, and to understand the associated flow physics. Firstly, two key geometric parameters, namely the bump crest location and the bump height, were optimized to trade off shock control and laminar flow. The optimized 2D bump results in 8.19% total drag reduction in the wing section, specifically, 8.61% pressure drag reduction and 6.23% viscous drag reduction. The total drag coefficient of the aircraft reduces by 8.12 counts while the lift slightly increases. Then, the robustness of the bump at off-design conditions was verified as well. Finally, the 2D bump was converted to 3D bumps according to the transonic area rule to explore more alternative designs, and it was found that the two have similar performances, confirming the effectiveness of the transonic area rule applied in the shock-control-bump design.