An application of neural networks to the prediction of aerodynamic coefficients of aerofoils and wings

Balla, Kensley; Sevilla, Rubén; Hassan, O.; Morgan, K.

doi:10.1016/j.apm.2021.03.019

Cited by 32 publications

(11 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is mainly attributed to the fact that in both cases the maximum number of training cases is 160 but this example contains three times more parameters. In addition, it is worth noting that the parameters considered in this example are geometric parameters and it is usually more difficult to generate reduced order models, when compared to flow conditions [12,35].…”

Section: Near-optimal Mesh Predictions On a Variable Wing Geometry At...mentioning

confidence: 99%

“…Despite the use of machine learning algorithms in the computational engineering field has increased exponentially during the last years, the focus seems to be on learning to predict physical phenomena [11][12][13]. The use of machine learning to assist the mesh generation has attracted much less attention, but related work can be found in the literature.…”

Section: Introductionmentioning

confidence: 99%

“…denotes the indices of local sources in S i , the indices of all local sources is L = L 1 ∪ … ∪ L C and the indices of the global sources is G = {1, … , |G|} , where G is the list of global sources.Algorithm 2 describes the developed process to combine the sets of local sources into one set of global sources. The set of global sources are further tuned for each input set of parameters to produce the required mesh to capture the given solution (12). …”

mentioning

confidence: 99%

See 2 more Smart Citations

Meshing using neural networks for improving the efficiency of computer modelling

Lock

Hassan

Sevilla

et al. 2023

Engineering with Computers

Self Cite

View full text Add to dashboard Cite

This work presents a novel approach capable of predicting an appropriate spacing function that can be used to generate a near-optimal mesh suitable for simulation. The main objective is to make use of the large number of simulations that are nowadays available, and to alleviate the time-consuming mesh generation stage by minimising human intervention. For a given simulation, a technique to produce a set of point sources that leads to a mesh capable of capturing all the features of the solution is proposed. In addition, a method to combine all sets of sources for the simulations available is devised. The global set of sources is used to train a neural network that, for some design parameters (e.g., flow conditions, geometry), predicts the characteristics of the sources. Numerical examples, in the context of three dimensional inviscid compressible flows, are considered to demonstrate the potential of the proposed approach. It is shown that accurate predictions of the required spacing function can be produced, even with reduced training datasets. In addition, the predicted near-optimal meshes are utilised to compute flow solutions, and the results show that the computed aerodynamic coefficients are within the required accuracy for the aerospace industry. An analysis is also presented to demonstrate that the proposed method lies in the category of green AI research, meaning that computational resources and time are substantially reduced with this approach, when compared to current practice in industry.

show abstract

Section: Near-optimal Mesh Predictions On a Variable Wing Geometry At...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Meshing using neural networks for improving the efficiency of computer modelling

Lock

Hassan

Sevilla

et al. 2023

Engineering with Computers

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this section we will list some of the applications of physics-informed neural networks, divided into following categories: that can be challenging to achieve using traditional methods alone. One noteworthy application is in predicting aerodynamic characteristics [6]. By leveraging PINNs, researchers can analyze and optimize the shapes of aircraft, vehicles, and other objects interacting with a fluid medium.…”

Section: Applicationsmentioning

confidence: 99%

Overview of Physics-Informed Neural Networks Applications

Milićević,

Ivanović,

Stojanović

et al. 2023

View full text Add to dashboard Cite

When simulating various physical phenomena, the law of the phenomenon is often known in advance, in the form of a partial differential equation, that needs to be solved. Numerical methods, such as the finite element method, have been developed over decades, and these methods approximate the solution to the partial differential equation. However, these methods can be computationally demanding. On the oth- er hand, neural networks, can provide predictions that approximate the given partial differential equation. Neural networks are computationally more efficient than numerical methods, but they often face issues of generalization and consequently problems with solution accuracy. Insufficient generalization, among other things, can result from data collected from numerical simulations. In the last few years, physics-informed neural networks are being developed, for which it’s not necessary to gather data from simulations. These networks use automatic differentiation and during training, they minimize the residuals of the partial differ- ential equation, its initial, and boundary conditions. After training, these neural networks can be used as a replacement for traditional numerical solvers.

show abstract

“…Back propagation neural network is one of the most common applications of ANN to predict the certain outputs based on the training of input parameters (Hagan et al, 2002). The ANN prediction method is successfully applied to various fields of engineering (Mitchell, 2003;Hagan et al, 2002;Balla et al, 2021;Do et al, 2020;Bagheripoor and Bisadi, 2013;Sattari et al, 2013). Pidaparti and Palakal (2015) developed a BP neural network to predicting the stress-strain behaviour of graphite-epoxy laminates based on a training experimental data set consisting of 959 points.…”

Section: Introductionmentioning

confidence: 99%

Prediction of mechanical solutions for a laminated LCEs system fusing an analytical model and neural networks

Wang

Yuan

et al. 2022

Journal of the Mechanical Behavior of Biomedical Materials

View full text Add to dashboard Cite

An application of neural networks to the prediction of aerodynamic coefficients of aerofoils and wings

Cited by 32 publications

References 57 publications

Meshing using neural networks for improving the efficiency of computer modelling

Meshing using neural networks for improving the efficiency of computer modelling

Overview of Physics-Informed Neural Networks Applications

Prediction of mechanical solutions for a laminated LCEs system fusing an analytical model and neural networks

Contact Info

Product

Resources

About