This page has only limited features, please log in for full access.

Dr. Shuyue Wang
Fudan University

Basic Info


Research Keywords & Expertise

0 Aerodynamics
0 Aircraft Design
0 Data Analysis
0 Computational Fluid Dynamic (CFD)
0 artificial intelligence

Honors and Awards

The user has no records in this section


Career Timeline

The user has no records in this section.


Short Biography

My academic interest is to perfectize the application of artificial intelligence in the field of aerodynamics.

Following
Followers
Co Authors
The list of users this user is following is empty.
Following: 0 users

Feed

Research article
Published: 22 March 2021 in Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering
Reads 0
Downloads 0

Geometrical representation method plays a fundamental role in aerodynamic design in that it makes preparation for design space. A good design space should be composed of design variables that are more likely to attain the solution to the problem than others. This study finds that due to the characteristics of Bernstein polynomials, a conventional class-shape transformation (CST) geometrical representation method is insufficiently focused on the leading-edge region of airfoils/wings. However, more aerodynamic attention is required there because it has strong relationship with the aerodynamic performance of whole geometry. The lack of design variables assigned to the leading-edge region is likely to compromise the effort in finding better optimization results in design space. While maintaining the convenience and accuracy of conventional CST, this study proposes two types of modifications to add more aerodynamic insights into the leading-edge region: (1) an approach of supplementary vertical CST aiming to describe the leading-edge region upon the fitting result of conventional CST; (2) an approach of globally transforming airfoil surfaces into a single-value function with respect to x-direction so that the leading-edge region avoids being split up into two separate parts. With those two modifications, the leading edge can be put to the center of geometric description by rotating the local coordinate system after tackling some other issues that come with the operation. Modification 1 is intuitive, although it requires additional attention to some parameters for the continuity between the leading-edge region and other regions of the airfoil. Modification 2 is convenient to implement, but has limitations on accuracy control because the result of shape error has to account for the introduction global transforming function. Two modifications are illustrated, and their applications are discussed in the study, showing the perspective of being utilized in aerodynamic design that involves delicate difference of aerodynamic performance brought by variations of leading-edge shape.

ACS Style

Shuyue Wang; Cong Wang; Gang Sun. Modifications of class-shape transformation driven by aerodynamic concerns over leading-edge region. Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering 2021, 1 .

AMA Style

Shuyue Wang, Cong Wang, Gang Sun. Modifications of class-shape transformation driven by aerodynamic concerns over leading-edge region. Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering. 2021; ():1.

Chicago/Turabian Style

Shuyue Wang; Cong Wang; Gang Sun. 2021. "Modifications of class-shape transformation driven by aerodynamic concerns over leading-edge region." Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering , no. : 1.

Journal article
Published: 24 December 2020 in Applied Sciences
Reads 0
Downloads 0

The multi-objective optimization of compressor cascade rotor blade is important for aero engine design. Many conventional approaches are thus proposed; however, they lack a methodology for utilizing existing design data/experiences to guide actual design. Therefore, the conventional methods require and consume large computational resources due to their need for large numbers of stochastic cases for determining optimization direction in the design space of problem. This paper proposed a Reinforcement Learning method as a new approach for compressor blade multi-objective optimization. By using Deep Deterministic Policy Gradient (DDPG), the approach modifies the blade profile as an intelligent designer according to the design policy: it learns the design experience of cascade blade as accumulated knowledge from interaction with the computation-based environment; the design policy can thus be updated. The accumulated computational data is therefore transformed into design experience and policies, which are directly applied to the cascade optimization, and the good-performance profiles can be thus approached. In a case study provided in this paper, the proposed approach is applied on a blade profile, which is thus optimized in terms of total pressure loss and laminar flow area. Compared with the initial profile, the total pressure loss coefficient is reduced by 3.59%, and the relative laminar flow area at the suction surface is improved by 25.4%.

ACS Style

Sheng Qin; Shuyue Wang; Liyue Wang; Cong Wang; Gang Sun; Yongjian Zhong. Multi-Objective Optimization of Cascade Blade Profile Based on Reinforcement Learning. Applied Sciences 2020, 11, 106 .

AMA Style

Sheng Qin, Shuyue Wang, Liyue Wang, Cong Wang, Gang Sun, Yongjian Zhong. Multi-Objective Optimization of Cascade Blade Profile Based on Reinforcement Learning. Applied Sciences. 2020; 11 (1):106.

Chicago/Turabian Style

Sheng Qin; Shuyue Wang; Liyue Wang; Cong Wang; Gang Sun; Yongjian Zhong. 2020. "Multi-Objective Optimization of Cascade Blade Profile Based on Reinforcement Learning." Applied Sciences 11, no. 1: 106.

Journal article
Published: 21 October 2020 in European Journal of Mechanics - B/Fluids
Reads 0
Downloads 0

Bioinspired grooved surface structure design has been widely used as an efficient passive flow control method in drag reduction. The total drag of plate with grooved surface structure can be decomposed into friction and pressure drag. In this paper, the relationship between them and the distribution of vortex structure in flow field has been analyzed for obtaining the drag reduction mechanism of grooved surface structure. The concept of ‘Vortex-Driven Design’ is proposed to improve the performance of conventional periodic single-level grooved surface structure. A design scheme of micro-nano scale nested-grooved surface structure with better drag reduction performance is given. The authors conduct numerical simulation of rectangular nested-grooved surface structure in laminar flow considering rarefaction based on Lattice Boltzmann Method at high Knudsen number. The results show that the nested-grooved surface structure induces higher complexity in the secondary vortex structure, and that the changes of vorticity distribution and flow characteristics drive the changes of velocity distribution and shear stress in the grooved surface. Compared with conventional grooved surface structure, the average friction drag of the surface is further reduced. Two geometric optimization cases of the conventional grooved surface and nested-grooved surface are realized by Genetic Algorithm, showing that the maximum drag reduction rate of the optimal nested-grooved surface can reach 18.76% while that of the optimal conventional grooved surface only reaches 13.61%. Based on ‘Vortex-Driven Design’, an innovative material improvement method for drag reduction is proposed as a new direction for subsequent research on microstructure in terms of drag reduction and energy conservation.

ACS Style

Liyue Wang; Cong Wang; Shuyue Wang; Gang Sun; Bo You. Design and analysis of micro-nano scale nested-grooved surface structure for drag reduction based on ‘Vortex-Driven Design’. European Journal of Mechanics - B/Fluids 2020, 85, 335 -350.

AMA Style

Liyue Wang, Cong Wang, Shuyue Wang, Gang Sun, Bo You. Design and analysis of micro-nano scale nested-grooved surface structure for drag reduction based on ‘Vortex-Driven Design’. European Journal of Mechanics - B/Fluids. 2020; 85 ():335-350.

Chicago/Turabian Style

Liyue Wang; Cong Wang; Shuyue Wang; Gang Sun; Bo You. 2020. "Design and analysis of micro-nano scale nested-grooved surface structure for drag reduction based on ‘Vortex-Driven Design’." European Journal of Mechanics - B/Fluids 85, no. : 335-350.

Journal article
Published: 27 August 2020 in Applied Sciences
Reads 0
Downloads 0

Design requirement is as important in aerodynamic design as in other industries because it sets up the objective for the samples in design space to approach. Natural Laminar Flow (NLF) optimization belongs to the type of aerodynamic design problems featured by the combination of distinct aerodynamic performance, where the design requirement is often formulated in form of summation of laminar-related performance and pressure drag performance with different weight assignment according to different perspectives. However, the formulations are rather experience-oriented and are decided non-quantitatively. Inspired by data manipulation approaches in design space (spanned by design variables of geometrical representation parameters) in many aerodynamic designs, this paper proposes new formulations of design requirement in NLF optimization via consideration of objective space (projection of design space through aerodynamics) and shows the impact of the corresponding formulation of design requirement to the result of NLF optimization in cases of transonic airfoil and aero engine compressor blade design from two perspectives: Pareto front convergence and improving effect of accessory performance. The paper uses Principal Component Analysis (PCA) to obtain the eigenvectors of objective space to extract the intrinsic information about specific problem. The method is realized in two cases with satisfactory result.

ACS Style

Shuyue Wang; Cong Wang; Gang Sun. The Objective Space and the Formulation of Design Requirement in Natural Laminar Flow Optimization. Applied Sciences 2020, 10, 5943 .

AMA Style

Shuyue Wang, Cong Wang, Gang Sun. The Objective Space and the Formulation of Design Requirement in Natural Laminar Flow Optimization. Applied Sciences. 2020; 10 (17):5943.

Chicago/Turabian Style

Shuyue Wang; Cong Wang; Gang Sun. 2020. "The Objective Space and the Formulation of Design Requirement in Natural Laminar Flow Optimization." Applied Sciences 10, no. 17: 5943.

Review
Published: 26 July 2019 in Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering
Reads 0
Downloads 0

Artificial neural network surrogate modeling with its economic computational consumption and accurate generalization capabilities offers a feasible approach to aerodynamic design in the field of rapid investigation of design space and optimal solution searching. This paper reviews the basic principle of artificial neural network surrogate modeling in terms of data treatment and configuration setup. A discussion of artificial neural network surrogate modeling is held on different objectives in aerodynamic design applications, various patterns of realization via cutting-edge data technique in numerous optimizations, selection of network topology and types, and other measures for improving modeling. Then, new frontiers of modern artificial neural network surrogate modeling are reviewed with regard to exploiting the hidden information for bringing new perspectives to optimization by exploring new data form and patterns, e.g. quick provision of candidates of better aerodynamic performance via accumulated database instead of random seeding, and envisions of more physical understanding being injected to the data manipulation.

ACS Style

Gang Sun; Shuyue Wang. A review of the artificial neural network surrogate modeling in aerodynamic design. Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering 2019, 233, 5863 -5872.

AMA Style

Gang Sun, Shuyue Wang. A review of the artificial neural network surrogate modeling in aerodynamic design. Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering. 2019; 233 (16):5863-5872.

Chicago/Turabian Style

Gang Sun; Shuyue Wang. 2019. "A review of the artificial neural network surrogate modeling in aerodynamic design." Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering 233, no. 16: 5863-5872.

Journal article
Published: 01 July 2019 in Journal of Aerospace Engineering
Reads 0
Downloads 0

Natural laminar flow (NLF) design is widely used to reduce skin friction drag to improve aircraft aerodynamic performance. In this paper, a differential evolution (DE) algorithm was applied to a NLF-designed transonic nacelle. The class shape transformation (CST) method was tested in terms of accuracy before being adopted as the geometry parameterization method that describes three longitudinal profiles constructing the nacelle surface. The purpose of this optimization is to extend the laminar length of each longitudinal profile of the nacelle while maintaining pressure drag under a preset limit. A high-fidelity computational fluid dynamics (CFD) solver was used for accurate laminar/turbulence transition prediction. It was tested in terms of pressure distribution and particularly laminar transition prediction. The whole process was executed via a Python version 3 script automatically. The laminar length was extended on longitudinal profiles after DE operation. The laminar area of the optimized nacelle surface was increased by 16.64% and total drag coefficient was decreased by 11.6 counts.

ACS Style

Shuyue Wang; Gang Sun; Chenghong Li. Natural Laminar Flow Optimization of Transonic Nacelle Based on Differential Evolution Algorithm. Journal of Aerospace Engineering 2019, 32, 06019001 .

AMA Style

Shuyue Wang, Gang Sun, Chenghong Li. Natural Laminar Flow Optimization of Transonic Nacelle Based on Differential Evolution Algorithm. Journal of Aerospace Engineering. 2019; 32 (4):06019001.

Chicago/Turabian Style

Shuyue Wang; Gang Sun; Chenghong Li. 2019. "Natural Laminar Flow Optimization of Transonic Nacelle Based on Differential Evolution Algorithm." Journal of Aerospace Engineering 32, no. 4: 06019001.

Journal article
Published: 20 August 2018 in Aerospace Science and Technology
Reads 0
Downloads 0

The concept of stall lift robustness for high-lift device (HLD) measures the stability of lift values under a series of angles of attack (AoA) around stall, which plays a significant role in flight safety. In this article, a stall lift robustness design with the consideration of aerodynamic constraints (stall AoA, average lift, etc.) is carried out, where design targets are set as a series of lift values on Lift-AoA curve. A Principle Component Analysis(PCA)-Artificial Neutral Network(ANN)-based inverse design model is introduced. The design targets are transformed by PCA for data dimension reduction. Then, the new set of design targets are input into the surrogate model of ANN, and corresponding geometry of new HLD is predicted. The ANN is constructed through database and sample points are screened considering lift unsteadiness. The design procedure is iterated to meet the design accuracy. The process of stall lift robustness design with the proposed model is discussed in this article, and the design results are validated by Detached-Eddy Simulation (DES).

ACS Style

Xinyu Wang; Shuyue Wang; Jun Tao; Gang Sun; Jun Mao. A PCA–ANN-based inverse design model of stall lift robustness for high-lift device. Aerospace Science and Technology 2018, 81, 272 -283.

AMA Style

Xinyu Wang, Shuyue Wang, Jun Tao, Gang Sun, Jun Mao. A PCA–ANN-based inverse design model of stall lift robustness for high-lift device. Aerospace Science and Technology. 2018; 81 ():272-283.

Chicago/Turabian Style

Xinyu Wang; Shuyue Wang; Jun Tao; Gang Sun; Jun Mao. 2018. "A PCA–ANN-based inverse design model of stall lift robustness for high-lift device." Aerospace Science and Technology 81, no. : 272-283.

Journal article
Published: 31 October 2017 in Aerospace Science and Technology
Reads 0
Downloads 0

Aircraft design today requires large amount of CFD calculation. For example when Natural Laminar Flow technique is applied to reduce aircraft skin friction drag by extending laminar length over surface, flowfield calculation related with airfoil laminar transition is computationally intense. Situations like this make iterative trial-and-error approach very inefficient. In order to improve this, this paper aims to exploit airfoil database of geometry and aerodynamic performance (from accumulated experiment and CFD calculation results) based on Artificial Neural Network to develop the approach of database self-expansion. It can generate airfoils with better aerodynamic performance from original database, so that the new airfoils can be applied to improve local aerodynamic performance of aircraft. The motive of the approach is to utilize the resource of accumulated optimization products in order to aid aircraft design. In this paper, we will discuss its application in laminar length extension over the surface of nacelle and wing. Geometry description in preparation of database establishment, configuration of network training, and workflow will be described in the paper.

ACS Style

Shuyue Wang; Gang Sun; Wanchun Chen; Yongjian Zhong. Database self-expansion based on artificial neural network: An approach in aircraft design. Aerospace Science and Technology 2017, 72, 77 -83.

AMA Style

Shuyue Wang, Gang Sun, Wanchun Chen, Yongjian Zhong. Database self-expansion based on artificial neural network: An approach in aircraft design. Aerospace Science and Technology. 2017; 72 ():77-83.

Chicago/Turabian Style

Shuyue Wang; Gang Sun; Wanchun Chen; Yongjian Zhong. 2017. "Database self-expansion based on artificial neural network: An approach in aircraft design." Aerospace Science and Technology 72, no. : 77-83.

Journal article
Published: 10 February 2015 in Aerospace Science and Technology
Reads 0
Downloads 0

The numerical search for the optimum shape of airfoil/wing geometry is of great interest for aircraft and turbomachinery designers. However the conventional method of design and optimization, which is to repeat the process of modifying airfoil/wing geometry data based on the flow field calculation of initial geometry, is computationally intensive and time-costly. In lieu of this, this article introduces an applicable airfoil/wing inverse design method with the help of Artificial Neural Network and airfoil/wing database, so that a properly trained network should directly provide an airfoil/wing that fits the required aerodynamical features. Repeating the process itself being avoided, the design efficiency improves. This article will present the detail of setting up the airfoil/wing inverse design method and provide the verification of the applicability of the approach.

ACS Style

Gang Sun; Yanjie Sun; Shuyue Wang. Artificial neural network based inverse design: Airfoils and wings. Aerospace Science and Technology 2015, 42, 415 -428.

AMA Style

Gang Sun, Yanjie Sun, Shuyue Wang. Artificial neural network based inverse design: Airfoils and wings. Aerospace Science and Technology. 2015; 42 ():415-428.

Chicago/Turabian Style

Gang Sun; Yanjie Sun; Shuyue Wang. 2015. "Artificial neural network based inverse design: Airfoils and wings." Aerospace Science and Technology 42, no. : 415-428.