Estimation of Reynolds number for flows around cylinders with lattice Boltzmann methods and artificial neural networks

Carrillo, M.; Que, Ulices; González, José Antonio García-Cruces

doi:10.1103/physreve.94.063304

Cited by 7 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Introducing N sample training data examples (i.e., input-output pairs), the weights and biases can be computed in a supervised learning framework using either well established iterative back propagation methods [49] or pseudoinverse approaches [34]. As mentioned previously, the ANN architecture is trained by utilizing an ELM approach proposed in [33] for extremely fast training of an SLFN.…”

Section: A Extreme Learning Machinementioning

confidence: 99%

Extreme learning machine for reduced order modeling of turbulent geophysical flows

San

Maulik

2018

Phys. Rev. E

View full text Add to dashboard Cite

We investigate the application of artificial neural networks to stabilize proper orthogonal decomposition-based reduced order models for quasistationary geophysical turbulent flows. An extreme learning machine concept is introduced for computing an eddy-viscosity closure dynamically to incorporate the effects of the truncated modes. We consider a four-gyre wind-driven ocean circulation problem as our prototype setting to assess the performance of the proposed data-driven approach. Our framework provides a significant reduction in computational time and effectively retains the dynamics of the full-order model during the forward simulation period beyond the training data set. Furthermore, we show that the method is robust for larger choices of time steps and can be used as an efficient and reliable tool for long time integration of general circulation models.

show abstract

Section: A Extreme Learning Machinementioning

confidence: 99%

Extreme learning machine for reduced order modeling of turbulent geophysical flows

San

Maulik

2018

Phys. Rev. E

View full text Add to dashboard Cite

show abstract

“…The simulation of the two dimensional flow around an obstacle, was performed constructing a numerical code based on the lattice Boltzmann method (LBM) as in [29]. The LBM is very popular because it is easy to implement and it has a high capacity to perform computational simulations in a wide variety of physical problems [30][31][32], mainly applied in computational fluid dynamics [33,34].…”

Section: Numerical Simulationsmentioning

confidence: 99%

“…We have chosen the physical units such that the numerical domain corresponds to a total length of L y = 0.41m in the vertical direction and L x = 2.5m along the horizontal. We considered a Poiseuille income fluid flow in a stationary regime with a density of ρ = 10 3 kg/m 3 , an a kinematic viscosity of ν = 10 −3 m 2 /s, as used in [29]. The location of all the studied obstacles is at x = 0.6m of the pipe, and their position over the y-axis will be described in the following section.…”

Section: Numerical Simulationsmentioning

confidence: 99%

Recognition of an obstacle in a flow using artificial neural networks

Carrillo¹,

Que²,

González³

et al. 2017

Phys. Rev. E

Self Cite

View full text Add to dashboard Cite

In this work a series of artificial neural networks (ANNs) has been developed with the capacity to estimate the size and location of an obstacle obstructing the flow in a pipe. The ANNs learn the size and location of the obstacle by reading the profiles of the dynamic pressure q or the x component of the velocity v_{x} of the fluid at a certain distance from the obstacle. Data to train the ANN were generated using numerical simulations with a two-dimensional lattice Boltzmann code. We analyzed various cases varying both the diameter and the position of the obstacle on the y axis, obtaining good estimations using the R^{2} coefficient for the cases under study. Although the ANN showed problems with the classification of very small obstacles, the general results show a very good capacity for prediction.

show abstract

“…Deep learning algorithms are also becoming useful analytical tools for microscopic image analysis 15,16 and micro-praticle tracking 17 . Neural networks can be employed to estimate Reynolds number for flows around cylinders 18 and also for drag prediction of arbitrary 2D shapes in laminar flow at low Reynolds number 19 . ML algorithms can be exploited to determine the order parameter, the temperature of a sample 20 , liquid crystal phases 21 and pitch length of cholesteric liquid crystals 22 from polarized light microscopy images as well as to identify types of topological defects in NLCs from the known director field 23 or to predict the specific heat of newly designed proteins 24 .…”

Section: Introductionmentioning

confidence: 99%

Neural networks determination of material elastic constants and structures in nematic complex fluids

Zaplotnik

Pišljar

Škarabot

et al. 2023

Preprint

View full text Add to dashboard Cite

Supervised machine learning and artificial neural network approaches can allow for the determination of selected material parameters or structures from a measurable signal without knowing the exact mathematical relationship between them. Here, we demonstrate that material nematic elastic constants and the initial structural material configuration can be found using sequential neural networks applied to the transmmited time-dependent light intensity through the nematic liquid crystal (NLC) sample under crossed polarizers. Specifically, we simulate multiple times the relaxation of the NLC from a random (qeunched) initial state to the equilibirum for random values of elastic constants and, simultaneously, the transmittance of the sample for monochromatic polarized light. The obtained time-dependent light transmittances and the corresponding elastic constants form a training data set on which the neural network is trained, which allows for the determination of the elastic constants, as well as the initial state of the director. Finally, we demonstrate that the neural network trained on numerically generated examples can also be used to determine elastic constants from experimentally measured data, finding good agreement between experiments and neural network predictions.

show abstract

Estimation of Reynolds number for flows around cylinders with lattice Boltzmann methods and artificial neural networks

Cited by 7 publications

References 27 publications

Extreme learning machine for reduced order modeling of turbulent geophysical flows

Extreme learning machine for reduced order modeling of turbulent geophysical flows

Recognition of an obstacle in a flow using artificial neural networks

Neural networks determination of material elastic constants and structures in nematic complex fluids

Contact Info

Product

Resources

About