Research on sparse identification method for aeroelastic dynamic response prediction

Article Mathematics

Machine-Learning Methods on Noisy and Sparse Data

Konstantinos Poulinakis et al.

Summary: This study compares machine-learning methods and cubic splines on their ability to handle sparse and noisy training data. The results show that cubic splines provide more precise interpolation than deep neural networks and multivariate adaptive regression splines with very sparse data. However, machine-learning models show robustness to noise and can outperform splines after reaching a threshold of training data. The study aims to provide a general framework for interpolating one-dimensional signals, often obtained from complex scientific simulations or laboratory experiments.

MATHEMATICS (2023)

添加到收藏夹

Article Mechanics

Deep learning reconstruction of pressure fluctuations in supersonic shock-boundary layer interaction

Konstantinos Poulinakis et al.

Summary: The long short-term memory deep-learning model is applied to reconstruct near-wall pressure fluctuations from reduced datasets, allowing predictions using less expensive simulations and experiments.

PHYSICS OF FLUIDS (2023)

添加到收藏夹

Article Physics, Multidisciplinary

Linear and nonlinear combined aerodynamic reduced order model based on residual network framework

Hui Qi et al.

Summary: This letter proposes a residual network aerodynamic reduced order model (ROM) framework based on CFD sample data to predict the aerodynamic characteristics of an airfoil. The input information is extracted and integrated through two transmission methods to complete regression prediction. The ROM framework shows effectiveness in predicting strongly nonlinear hysteresis loops and can be applied to qualitative interpretation of complex flow phenomena and aeroelastic analysis.

EPL (2022)

添加到收藏夹

Article Engineering, Mechanical