☆ 4.7 Article

Airfoil design and surrogate modeling for performance prediction based on deep learning method

PHYSICS OF FLUIDS (2022)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Engineering, Aerospace

Non-intrusive reduced order modeling for flowfield reconstruction based on residual neural network

Wenjun Ma et al.

Summary: A non-intrusive reduced order model based on residual neural network is proposed for parameterized flows, which reconstructs the unknown flowfield of the target problem online with a mapping relationship constructed in the offline stage. By employing proper orthogonal decomposition and a two-step training strategy, the model is superior to feedforward neural network-based models in terms of accuracy and robustness, especially for problems of high sensitivity with respect to flow parameters.

ACTA ASTRONAUTICA (2021)

添加到收藏夹

Article Engineering, Aerospace

Turbulence closure for high Reynolds number airfoil flows by deep neural networks

Linyang Zhu et al.

Summary: This study combines turbulence big data with artificial intelligence to construct black-box algebraic models for turbulence simulation. By integrating scaling analysis and deep neural networks, a model with good generalization ability is successfully built, showing promising prospects for turbulence modeling using machine learning methods.

AEROSPACE SCIENCE AND TECHNOLOGY (2021)

添加到收藏夹

Article Thermodynamics

Supervised learning method for the physical field reconstruction in a nanofluid heat transfer problem

Tianyuan Liu et al.

Summary: This paper introduces a supervised learning method using CNN to predict physical fields and infer heat transfer characteristics. The data-driven approach establishes a mapping from low-dimensional measurable information to full physical fields. The method shows promising applications in heat transfer research.

INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER (2021)

添加到收藏夹

Article Mechanics

A point-cloud deep learning framework for prediction of fluid flow fields on irregular geometries

Ali Kashefi et al.

Summary: The study introduces a novel deep learning framework for flow field predictions in irregular domains, using a neural network based on the PointNet architecture to map between spatial positions and CFD quantities. The network inherits desirable features of unstructured meshes, accurately represents object geometry, and preserves the accuracy of CFD data without data interpolation. The new approach outperforms existing methods in terms of speed and accuracy.

PHYSICS OF FLUIDS (2021)

添加到收藏夹

Article Engineering, Aerospace

Enhanced data efficiency using deep neural networks and Gaussian processes for aerodynamic design optimization

S. Ashwin Renganathan et al.

Summary: Adjoint-based optimization methods are suitable for aerodynamic shape design of highly parametrized geometries but can be costly to develop and implement. A machine learning enabled framework is proposed in this study to replace expensive adjoint solvers while maintaining predictive accuracy. This framework offers a more cost-effective solution for high-fidelity simulation based aerodynamic shape optimization.

AEROSPACE SCIENCE AND TECHNOLOGY (2021)

添加到收藏夹

Article Engineering, Aerospace

Surrogate-based aerodynamic shape optimization for delaying airfoil dynamic stall using Kriging regression and infill criteria

Vishal Raul et al.

Summary: The dynamic stall phenomenon is characterized by the formation of a leading-edge vortex, which impacts the structural strength and life of a system. Aerodynamic shape optimization provides a cost-effective method to delay or mitigate these characteristics, but it requires time-consuming CFD simulations. A surrogate-based optimization technique is proposed in this work to reduce the computational cost of ASO for airfoil dynamic stall characteristics.

AEROSPACE SCIENCE AND TECHNOLOGY (2021)

添加到收藏夹

Article Engineering, Aerospace

Dual-convolutional neural network based aerodynamic prediction and multi-objective optimization of a compact turbine rotor

Yuqi Wang et al.

Summary: With the development of neural network technology, the research hotspot in aerodynamic shape optimization has shifted towards surrogate models and dimensionality reduction strategies based on machine learning. This study successfully established the Dual Convolutional Neural Network (Dual-CNN) for predicting aerodynamic performances of aero-engine turbines, showing higher accuracy compared to traditional surrogate models.

AEROSPACE SCIENCE AND TECHNOLOGY (2021)

添加到收藏夹

Article Engineering, Aerospace

Rapid airfoil design optimization via neural networks-based parameterization and surrogate modeling

Xiaosong Du et al.

Summary: The aerodynamic optimization based on CFD reduces design time significantly compared with manual design but can still take hours to converge. A fast, interactive design framework is proposed to complete airfoil aerodynamic optimization within seconds, using a B-spline-based generative adversarial network for shape parameterization and a mixture of multilayer perceptron, recurrent neural networks, and experts for surrogate modeling. The framework's optimization results align well with those from direct CFD-based optimizations and evaluations for both subsonic and transonic conditions.

AEROSPACE SCIENCE AND TECHNOLOGY (2021)

添加到收藏夹

Article Mechanics

A deep learning based prediction approach for the supercritical airfoil at transonic speeds

Di Sun et al.

Summary: The traditional methods for aircraft aerodynamic properties are time-consuming, but the deep learning technique is efficient in handling high dimensional parameters and describing compressible flow structures. This study proposed an accurate prediction approach based on deep neural networks for compressible flows over transonic airfoils, which showed high resolution and efficiency and has potential for optimization processes.

PHYSICS OF FLUIDS (2021)

添加到收藏夹

Article Mechanics

Flow field prediction of supercritical airfoils via variational autoencoder based deep learning framework

Jing Wang et al.

Summary: Researchers developed a systematic method based on generative deep learning to extract flow field features and predict steady flow fields around airfoils. They used a VAE network to extract representative features of the flow fields and mapped airfoil shapes to features via an MLP model. The proposed method achieved accurate and generalized performance in reconstructing and predicting flow fields around supercritical airfoils.

PHYSICS OF FLUIDS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

CNNFOIL: convolutional encoder decoder modeling for pressure fields around airfoils

Cihat Duru et al.

Summary: In this study, a new approach based on neural networks is proposed for estimating the pressure field around an airfoil, achieving a high accuracy of 88% for unseen airfoil shapes and significant speed-up compared to CFD simulations. The model allows for performance analysis of different airfoils and the effect of shock, showing promise in accurately capturing flow patterns.

NEURAL COMPUTING & APPLICATIONS (2021)

添加到收藏夹

Review Mechanics

Machine Learning for Fluid Mechanics

Steven L. Brunton et al.

ANNUAL REVIEW OF FLUID MECHANICS, VOL 52 (2020)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

A deep learning approach for efficiently and accurately evaluating the flow field of supercritical airfoils

Haizhou Wu et al.

COMPUTERS & FLUIDS (2020)

添加到收藏夹

Article Mechanics

Machine learning for nonintrusive model order reduction of the parametric inviscid transonic flow past an airfoil

S. Ashwin Renganathan et al.

PHYSICS OF FLUIDS (2020)

添加到收藏夹

Article Engineering, Aerospace

Fast pressure distribution prediction of airfoils using deep learning

Xinyu Hui et al.

AEROSPACE SCIENCE AND TECHNOLOGY (2020)

添加到收藏夹

Article Engineering, Aerospace

Airfoil Design Parameterization and Optimization Using Bezier Generative Adversarial Networks

Wei Chen et al.

AIAA JOURNAL (2020)

添加到收藏夹

Article Mechanics

CNN-LSTM based reduced order modeling of two-dimensional unsteady flows around a circular cylinder at different Reynolds numbers

Kazuto Hasegawa et al.

FLUID DYNAMICS RESEARCH (2020)

添加到收藏夹

Article Engineering, Aerospace

Deep neural network approach for fault detection and diagnosis during startup transient of liquid-propellant rocket engine

Soon-Young Park et al.

ACTA ASTRONAUTICA (2020)

添加到收藏夹

Article Mechanics

Transition effects on flow characteristics around a static two-dimensional airfoil

Rui Wang et al.

PHYSICS OF FLUIDS (2020)

添加到收藏夹

Article Engineering, Aerospace

Benchmark aerodynamic shape optimization with the POD-based CST airfoil parametric method

Xiaojing Wu et al.

AEROSPACE SCIENCE AND TECHNOLOGY (2019)

添加到收藏夹

Article Mechanics

Fast flow field prediction over airfoils using deep learning approach

Vinothkumar Sekar et al.

PHYSICS OF FLUIDS (2019)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Framework for design optimization using deep reinforcement learning

Kazuo Yonekura et al.

STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION (2019)

添加到收藏夹

Article Engineering, Aerospace

Convolutional neural network based combustion mode classification for condition monitoring in the supersonic combustor

Xiaobin Zhu et al.

ACTA ASTRONAUTICA (2019)

添加到收藏夹

Article Mathematics, Interdisciplinary Applications

Prediction of aerodynamic flow fields using convolutional neural networks

Saakaar Bhatnagar et al.

COMPUTATIONAL MECHANICS (2019)

添加到收藏夹

Article Engineering, Aerospace

Application of deep learning based multi-fidelity surrogate model to robust aerodynamic design optimization

Jun Tao et al.

AEROSPACE SCIENCE AND TECHNOLOGY (2019)

添加到收藏夹

Article Mechanics

Data-driven prediction of unsteady flow over a circular cylinder using deep learning

Sangseung Lee et al.

JOURNAL OF FLUID MECHANICS (2019)

添加到收藏夹

Article Engineering, Aerospace

A hybrid reduced-order framework for complex aeroelastic simulations

Jiaqing Kou et al.

AEROSPACE SCIENCE AND TECHNOLOGY (2019)

添加到收藏夹

Article Engineering, Aerospace

Flowfield Reconstruction Method Using Artificial Neural Network

Jian Yu et al.

AIAA JOURNAL (2019)

添加到收藏夹

Article Mechanics

Machine learning methods for turbulence modeling in subsonic flows around airfoils

Linyang Zhu et al.

PHYSICS OF FLUIDS (2019)

添加到收藏夹

Article Mechanics

A novel spatial-temporal prediction method for unsteady wake flows based on hybrid deep neural network

Renkun Han et al.

PHYSICS OF FLUIDS (2019)

添加到收藏夹

Review Engineering, Aerospace

A review of parametric approaches specific to aerodynamic design process

Tian-tian Zhang et al.

ACTA ASTRONAUTICA (2018)

添加到收藏夹

Review Computer Science, Artificial Intelligence

State-of-the-art in aerodynamic shape optimisation methods

S. N. Skinner et al.

APPLIED SOFT COMPUTING (2018)

添加到收藏夹

Article Engineering, Multidisciplinary

Topology optimization with closed B-splines and Boolean operations

Weihong Zhang et al.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2017)

添加到收藏夹

Review Chemistry, Analytical

Support Vector Machines for classification and regression

Richard G. Brereton et al.

ANALYST (2010)

添加到收藏夹

Review Computer Science, Interdisciplinary Applications

Survey of modeling and optimization strategies to solve high-dimensional design problems with computationally-expensive black-box functions

Songqing Shan et al.

STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION (2010)

添加到收藏夹

Article Operations Research & Management Science

An adaptive radial basis algorithm (ARBF) for expensive black-box global optimization

Kenneth Holmstrom

JOURNAL OF GLOBAL OPTIMIZATION (2008)

添加到收藏夹

Article Engineering, Aerospace

Efficient optimization design method using kriging model

S Jeong et al.

JOURNAL OF AIRCRAFT (2005)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.