Machine learning for flow field measurements: a perspective

Discetti, Stefano; Liu, Yingzheng

doi:10.1088/1361-6501/ac9991

Cited by 15 publications

(7 citation statements)

References 139 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the flourish development of artificial intelligence, its applications in fluid field are on the rise. Stefano Discetti and Liu summarized the applications and potential developments of machine learning techniques in flow field measurement [11]. For example, compared with traditional methods, automatic unsupervised PIV image preprocessing could lead to a reduction in human intervention.…”

Section: Introductionmentioning

confidence: 99%

A deep-learning image registration method for pressure-sensitive paint measurements

Di,

Gu,

Liu

et al. 2024

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Image registration is an essential step in the data processing of pressure-sensitive paint (PSP) measurements. As PSP technology is gradually expanded to increasingly harsh environments, it faces challenges such as severe image misalignment due to model deformations/motions, which pose difficulties to traditional featurebased registration algorithms. To improve registration accuracy and efficiency, we propose an end-to-end image registration method based on deep learning. Initially, a PSP dataset based on PSP images is constructed through data augmentation. Three types of residual network and three training strategies are then adopted to prepare the deep-learning model for automatic image registration. The optimal combination of the residual network and training strategy is selected for validation using fabricated PSP images and outperforms two traditional algorithms (i.e., the Sift and Watershed methods). Finally, the performance of the deep-learning method is compared with that of traditional algorithms adopting a new metric of the overlapping rate for assessing the registration accuracy on experimental PSP images. The results show that the deep learning method outperforms the traditional algorithms in terms of registration accuracy and robustness.

show abstract

Section: Introductionmentioning

confidence: 99%

A deep-learning image registration method for pressure-sensitive paint measurements

Di,

Gu,

Liu

et al. 2024

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…This feature has paved the way to explore the feasibility of applying ML to various problems in complex turbulent flows [10][11][12][13][14] [15]. Several ML-based methods have been introduced considering flow reconstruction from spatially limited or corrupted data [16]. Recently promising results have been reported by using end-to-end trained convolutional neural network (CNN)-based models [17][10] [18] and generative adversarial network (GAN)-based [19][20] [13][21][22] models.…”

Section: Introductionmentioning

confidence: 99%

Physics-guided deep reinforcement learning for flow field denoising

Yousif¹,

Zhang²,

Yang³

et al. 2023

Preprint

View full text Add to dashboard Cite

A multi-agent deep reinforcement learning (DRL)-based model is presented in this study to reconstruct flow fields from noisy data. A combination of the reinforcement learning with pixel-wise rewards (PixelRL), physical constraints represented by the momentum equation and the pressure Poisson equation and the known boundary conditions is utilised to build a physics-guided deep reinforcement learning (PGDRL) model that can be trained without the target training data. In the PGDRL model, each agent corresponds to a point in the flow field and it learns an optimal strategy for choosing pre-defined actions. The proposed model is efficient considering the visualisation of the action map and the interpretation of the model performance. The performance of the model is tested by utilising synthetic direct numerical simulation (DNS)-based noisy data and experimental data obtained by particle image velocimetry (PIV). Qualitative and quantitative results show that the model can reconstruct the flow fields and reproduce the statistics and the spectral content with commendable accuracy. These results demonstrate that the combination of DRL-based models and the known physics of the flow fields can potentially help solve complex flow reconstruction problems, which can result in a remarkable reduction in the experimental and computational costs.

show abstract

“…2023 b ). Several supervised and unsupervised ML-based methods have been proposed for flow reconstruction from spatially limited or corrupted data (Discetti & Liu 2022). Recently, promising results have been reported from using deep learning (DL) by applying end-to-end trained convolutional neural network (CNN)-based models (Fukami, Fukagata & Taira 2019; Liu et al.…”

Section: Introductionmentioning

confidence: 99%

Physics-constrained deep reinforcement learning for flow field denoising

Yousif,

Zhang,

et al. 2023

J. Fluid Mech.

View full text Add to dashboard Cite

A multi-agent deep reinforcement learning (DRL)-based model is presented in this study to reconstruct flow fields from noisy data. A combination of reinforcement learning with pixel-wise rewards, physical constraints represented by the momentum equation and the pressure Poisson equation, and the known boundary conditions is used to build a physics-constrained deep reinforcement learning (PCDRL) model that can be trained without the target training data. In the PCDRL model, each agent corresponds to a point in the flow field and learns an optimal strategy for choosing pre-defined actions. The proposed model is efficient considering the visualisation of the action map and the interpretation of the model operation. The performance of the model is tested by using direct numerical simulation-based synthetic noisy data and experimental data obtained by particle image velocimetry. Qualitative and quantitative results show that the model can reconstruct the flow fields and reproduce the statistics and the spectral content with commendable accuracy. Furthermore, the dominant coherent structures of the flow fields can be recovered by the flow fields obtained from the model when they are analysed using proper orthogonal decomposition and dynamic mode decomposition. This study demonstrates that the combination of DRL-based models and the known physics of the flow fields can potentially help solve complex flow reconstruction problems, which can result in a remarkable reduction in the experimental and computational costs.

show abstract

Machine learning for flow field measurements: a perspective

Cited by 15 publications

References 139 publications

A deep-learning image registration method for pressure-sensitive paint measurements

A deep-learning image registration method for pressure-sensitive paint measurements

Physics-guided deep reinforcement learning for flow field denoising

Physics-constrained deep reinforcement learning for flow field denoising

Contact Info

Product

Resources

About