Advances in Aerodynamics · 2022 · 38 citations · 25 references
EngineeringAerospace EngineeringComputer ScienceComputational Fluid DynamicsFluid DynamicsMachine LearningAirfoil TheoryComputational AerodynamicsDeep LearningFlight SimulationHypersonic AerodynamicsWing AerodynamicsAerodynamic ModelingAerodynamic OptimizationAerodynamic Shape ModelingAerodynamic Shape OptimizationAircraft Performance ModelingComputational Wing AerodynamicsConvolutional Neural NetworksFlight
Abstract Modeling high-dimensional aerodynamic data presents a significant challenge in aero-loads prediction, aerodynamic shape optimization, flight control, and simulation. This article develops a machine learning approach based on a convolutional neural network (CNN) to address this problem. A CNN can implicitly distill features underlying the data. The number of parameters to be trained can be significantly reduced because of its local connectivity and parameter-sharing properties, which is favorable for solving high-dimensional problems in which the training cost can be prohibitive. A hypersonic wing similar to the Sanger aerospace plane carrier wing is employed as the test case to demonstrate the CNN-based modeling method. First, the wing is parameterized by the free-form deformation method, and 109 variables incorporating flight status and aerodynamic shape variables are defined as model input. Second, more than 7000 sample points generated by the Latin hypercube sampling method are evaluated by performing computational fluid dynamics simulations using a Reynolds-averaged Navier–Stokes flow solver to obtain an aerodynamic database, and a CNN model is built based on the observed data. Finally, the well-trained CNN model considering both flight status and shape variables is applied to aerodynamic shape optimization to demonstrate its capability to achieve fast optimization at multiple flight statuses.
25
Gradient-based learning applied to document recognition
Yann LeCun, Léon Bottou, Yoshua Bengio et al. · Proceedings of the IEEE · 1998 · 58.2K citations · Full text
Learning representations by back-propagating errors
David E. Rumelhart, Geoffrey E. Hinton, Ronald J. Williams · Nature · 1986 · 30.9K citations
Understanding of a convolutional neural network
Saad Albawi, Tareq Abed Mohammed, Saad Al-Azawi · 2017 · 4K citations
Deep Learning Methods for Reynolds-Averaged Navier–Stokes Simulations of Airfoil Flows
Nils Thuerey, Konstantin Weißenow, Lukas Prantl et al. · AIAA Journal · 2019 · 572 citations · Full text