Key time steps selection for CFD data based on deep metric learning

Lu, Yutong; Wang, Yueqing; Sun, Dong; Deng, Liang; Wan, Yunbo; Wang, Fang

doi:10.1016/j.compfluid.2019.104318

Cited by 6 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Porter et al [49] uses an Autoencoder network to encode each time step to latent space and use a combination of arc-length-based and angle-based selection to choose frames in the dimension-reduced latent space. In the same year, Liu et al [34] proposed to employ Deep Metric Learning (DML) that utilizes a Siamese deep neural network to select key time steps in a supervised way.…”

Section: Related Work 21 Time Selection From Spatiotemporal Datamentioning

confidence: 99%

“…That is, the data between two selected time steps are linearly interpolated to generate full-duration data as the reconstructed data for comparison. To achieve this, dynamic programming-based methods [63,76] and deep learning-based methods [34,49] are two main approaches. These methods underscore the summerizability of the selected time steps, employing metrics like RMSE and SSIM to quantify the quality of the selection.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

SalienTime: User-driven Selection of Salient Time Steps for Large-Scale Geospatial Data Visualization

Chen,

Huang,

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

Section: Related Work 21 Time Selection From Spatiotemporal Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

SalienTime: User-driven Selection of Salient Time Steps for Large-Scale Geospatial Data Visualization

Chen,

Huang,

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…MS et al [19] introduced a composite CNN-RNN architecture to estimate the viscosity from flow sequences. Liu et al [20] designed Metric-Net to select a key time step for simulations.…”

Section: Introductionmentioning

confidence: 99%

Internal Flow Prediction in Arbitrary Shaped Channel Using Stream-Wise Bidirectional LSTM

Ko,

Choi,

Lee

2023

Applied Sciences

View full text Add to dashboard Cite

Deep learning (DL) methods have become the trend in predicting feasible solutions in a shorter time compared with traditional computational fluid dynamics (CFD) approaches. Recent studies have stacked numerous convolutional layers to extract high-level feature maps, which are then used for the analysis of various shapes under differing conditions. However, these applications only deal with predicting the flow around the objects located near the center of the domain, whereas most fluid-transport-related phenomena are associated with internal flows, such as pipe flows or air flows inside transportation vehicle engines. Hence, to broaden the scope of the DL approach in CFD, we introduced a stream-wise bidirectional (SB)-LSTM module that generates a better latent space from the internal fluid region by additionally extracting lateral connection features. To evaluate the effectiveness of the proposed method, we compared the results obtained using SB-LSTM to those of the encoder–decoder(ED) model and the U-Net model, as well as with the results when not using it. When SB-LSTM was applied, in the qualitative comparison, it effectively addressed the issue of erratic fluctuations in the predicted field values. Furthermore, in terms of quantitative evaluation, the mean relative error (MRE) for the x-component of velocity, y-component of velocity, and pressure was reduced by at least 2.7%, 4.7%, and 15%, respectively, compared to the absence of the SB-LSTM module. Furthermore, through a comparison of the calculation time, it was found that our approach did not undermine the superiority of the neural network’s computational acceleration effect.

show abstract

“…Ray and Hesthaven [1] designed an ANN to detect cells where there is a discontinuity in the results. Liu et al [2] established a method based on Deep Metric Learning (DML) to determine the optimal time-step value in non-stationary simulations. Bao et al [3] applied a physically driven approach to improve the modelling and simulation capability of a coarse mesh, and Hanna et al [4] designed a DL algorithm to predict and decrease the error of the results obtained on a coarse mesh.…”

Section: Introductionmentioning

confidence: 99%

Alternative Artificial Neural Network Structures for Turbulent Flow Velocity Field Prediction

et al. 2021

View full text Add to dashboard Cite

Turbulence in fluids has been a popular research topic for many years due to its influence on a wide range of applications. Computational Fluid Dynamics (CFD) tools are able to provide plenty of information about this phenomenon, but their computational cost often makes the use of these tools unfeasible. For that reason, in recent years, turbulence modelling using Artificial Neural Networks (ANNs) is becoming increasingly popular. These networks typically calculate directly the desired magnitude, having input information about the computational domain. In this paper, a Convolutional Neural Network (CNN) for predicting different magnitudes of turbulent flows around different geometries by approximating the equations of the Reynolds-Averaged Navier-Stokes (RANS)-based realizable k-ε two-layer turbulence model is proposed. Using that CNN, alternative network structures are proposed to predict the velocity fields of a turbulent flow around different geometries on a rectangular channel, with a preliminary stage to predict pressure and vorticity fields before calculating the velocity fields, and the obtained results are compared with the ones obtained with the basic structure. The results demonstrate that the proposed structures clearly outperform the basic one, especially when the flow becomes uncertain. In addition, considering the results, the best network configuration is proposed. That network is tested with a domain with multiple geometries and a domain with a narrowing of the channel, which are domains with different conditions from the training ones, showing fairly accurate predictions.

show abstract

Key time steps selection for CFD data based on deep metric learning

Cited by 6 publications

References 19 publications

SalienTime: User-driven Selection of Salient Time Steps for Large-Scale Geospatial Data Visualization

SalienTime: User-driven Selection of Salient Time Steps for Large-Scale Geospatial Data Visualization

Internal Flow Prediction in Arbitrary Shaped Channel Using Stream-Wise Bidirectional LSTM

Alternative Artificial Neural Network Structures for Turbulent Flow Velocity Field Prediction

Contact Info

Product

Resources

About