Data-driven modeling for unsteady aerodynamics and aeroelasticity
Aerodynamic modeling plays an important role in multiphysics and design problems, in
addition to experiment and numerical simulation, due to its low-dimensional representation …
addition to experiment and numerical simulation, due to its low-dimensional representation …
Application of a long short-term memory neural network for modeling transonic buffet aerodynamics
R Zahn, M Winter, M Zieher, C Breitsamter - Aerospace Science and …, 2021 - Elsevier
In the present work, a reduced-order modeling (ROM) framework based on a long short-term
memory (LSTM) neural network is applied for the prediction of transonic buffet …
memory (LSTM) neural network is applied for the prediction of transonic buffet …
Parametric Aeroelastic Reduced-Order Model with State-Consistence Enforcement
State-space reduced-order models (ROMs) constructed by traditional system identification
methods suffer from the state-inconsistence issue and poor ROM interpolatability for varying …
methods suffer from the state-inconsistence issue and poor ROM interpolatability for varying …
Deep learning surrogate for the temporal propagation and scattering of acoustic waves
A deep learning surrogate for the direct numerical temporal prediction of two-dimensional
acoustic waves propagation and scattering with obstacles is developed through an …
acoustic waves propagation and scattering with obstacles is developed through an …
Convolution and Volterra series approach to reduced-order modeling of unsteady aerodynamic loads
D Levin, KK Bastos, EH Dowell - AIAA Journal, 2022 - arc.aiaa.org
A combined approach of linear convolution and higher-order Volterra series (VS) to reduced-
order modeling of unsteady transonic aerodynamic loads is presented. Our framework offers …
order modeling of unsteady transonic aerodynamic loads is presented. Our framework offers …
Optimal sparsity in nonlinear non-parametric reduced order models for transonic aeroelastic systems
M Candon, E Hale, M Balajewicz… - arXiv preprint arXiv …, 2024 - arxiv.org
Machine learning and artificial intelligence algorithms typically require large amount of data
for training. This means that for nonlinear aeroelastic applications, where small training …
for training. This means that for nonlinear aeroelastic applications, where small training …
Multi-variable Volterra kernels identification using time-delay neural networks: application to unsteady aerodynamic loading
NCG De Paula, FD Marques - Nonlinear Dynamics, 2019 - Springer
In the last decades, the Volterra series theory has been used to construct reduced-order
models of nonlinear systems in engineering and applied sciences. For the particular case of …
models of nonlinear systems in engineering and applied sciences. For the particular case of …
New mathematical formulation of nonlinear unsteady wind loads on long-span bridge decks under nonstationary winds using time-delay neural network
K Ali - Journal of Structural Engineering, 2022 - ascelibrary.org
This paper presents a novel mathematical formulation of unsteady wind loads on bridge
decks by using the neural network technique while incorporating the concurrent effects of …
decks by using the neural network technique while incorporating the concurrent effects of …
Monitoring seismic damage via accelerometer data alone using Volterra series and genetic algorithm
An application of Volterra series in nonlinear system identification is presented in this paper.
This novel approach makes use of accelerometer data alone. The aim is to develop an …
This novel approach makes use of accelerometer data alone. The aim is to develop an …
基于深度算子神经网络的翼型失速颤振预测
席梓严， 戴玉婷， 黄广靖， 杨超 - 力学学报, 2024 - lxxb.cstam.org.cn
失速颤振是弹性结构大幅俯仰振动与动态失速气动力耦合所发生的一种单自由度失稳现象,
需有效预测其失稳分岔速度与失稳后的极限环振荡幅值. 针对NACA0012 翼型大幅俯仰运动气 …
需有效预测其失稳分岔速度与失稳后的极限环振荡幅值. 针对NACA0012 翼型大幅俯仰运动气 …