A rapid vortex identification method using fully convolutional segmentation network

Wang, Yueqing; Deng, Liang; Yang, Zhigong; Zhao, Dan; Wang, Fang

doi:10.1007/s00371-020-01797-6

Cited by 16 publications

(9 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, two new vortex identification methods-based CNN Vortex-Net [6] and Vortex-Seg-Net [7] have been proposed. Vortex-CNN uses local patches around each point in the velocity field to train the CNN network through the labels obtained by the global method, thereby transforming the vortex feature identification task into a binary classification problem.…”

Section: Machine Learning Methods For Vortex Identificationmentioning

confidence: 99%

“…Therefore, the accurate extraction of the vortex is of great significance for the study of the physical mechanism of the complex flow field. At present, conventional vortex feature extraction methods can be divided into three categories: local methods, global methods [2], and partial local-global hybrid methods [3][4][5][6][7].…”

Section: Introductionmentioning

confidence: 99%

“…To solve these problems, several methods based on convolutional neural networks are proposed. Such as Eddy-Net [16], fluid R-CNN [17], Vortex-CNN [6], and Vortex-Seg-Net [7]. These network methods are targeted at local points rather than the entire flow field of different sizes and shapes.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Vortex Identification Method Based on Extreme Learning Machine

Wang

Guo

Deng

et al. 2020

International Journal of Aerospace Engineering

Self Cite

View full text Add to dashboard Cite

Vortex identification and visualization are important means to understand the underlying physical mechanism of the flow field. Local vortex identification methods need to combine with the manual selection of the appropriate threshold, which leads to poor robustness. Global vortex identification methods are of high computational complexity and time-consuming. Machine learning methods are related to the size and shape of the flow field, which are weak in versatility and scalability. It cannot be extended and is suitable for flow fields of different sizes. Recently, proposed deep learning methods have long network training time and high computational complexity. Aiming at the above problems, we present a novel vortex identification method based on the Convolutional Neural Networks-Extreme Learning Machine (CNN-ELM). This method transforms the vortex identification problem into a binary classification problem, and can quickly, objectively, and robustly identify vortices from the flow field. A large number of experiments prove the effectiveness of our method, which can improve or supplement the shortcomings of existing methods.

show abstract

Section: Machine Learning Methods For Vortex Identificationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Vortex Identification Method Based on Extreme Learning Machine

Wang

Guo

Deng

et al. 2020

International Journal of Aerospace Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…Similarly, with respect to scientific visualization, specifically, flow visualization, the use of machine learning to perform several tasks has increased. For example, it has been widely used to detect flow field features such as eddies and vortices ( [5,12,14,37,39,58,61,63]). [33] utilized the convolutional neural networks (CNNs) to extract a robust frame of reference for unsteady two-dimensional (2D) vector fields.…”

Section: Flow Visualization Using Machine Learningmentioning

confidence: 99%

Exploratory Lagrangian-Based Particle Tracing Using Deep Learning

Han,

Sane,

Johnson

2021

Preprint

View full text Add to dashboard Cite

Time-varying vector fields produced by computational fluid dynamics simulations are often prohibitively large and pose challenges for accurate interactive analysis and exploration. To address these challenges, reduced Lagrangian representations have been increasingly researched as a means to improve scientific time-varying vector field exploration capabilities. This paper presents a novel deep neural network-based particle tracing method to explore time-varying vector fields represented by Lagrangian flow maps. In our workflow, in situ processing is first utilized to extract Lagrangian flow maps, and deep neural networks then use the extracted data to learn flow field behavior. Using a trained model to predict new particle trajectories offers a fixed small memory footprint and fast inference. To demonstrate and evaluate the proposed method, we perform an in-depth study of performance using a well-known analytical data set, the Double Gyre. Our study considers two flow map extraction strategies as well as the impact of the number of training samples and integration durations on efficacy, evaluates multiple sampling options for training and testing, and informs hyperparameter settings. Overall, we find our method requires a fixed memory footprint of 10.5 MB to encode a Lagrangian representation of a time-varying vector field while maintaining accuracy. For post hoc analysis, loading the trained model costs only two seconds, significantly reducing the burden of I/O when reading data for visualization. Moreover, our parallel implementation can infer one hundred locations for each of two thousand new pathlines across the entire temporal resolution in 1.3 seconds using one NVIDIA Titan RTX GPU.

show abstract

“…Liu et al [34] proposed a CNN-based shock-wave detection method and a novel loss function to optimize the detection results. Deng et al [35] and Wang et al [36] presented a novel vortex identification method based on a CNN. They utilized the instantaneous vorticity deviation (IVD) to label the ground truth vortex area for the proposed CNN-based model.…”

Section: B Flow Data Analysis Using Machine Learningmentioning

confidence: 99%

Deep Regression Network-Assisted Efficient Streamline Generation Method

Lee

Park

2021

IEEE Access

View full text Add to dashboard Cite

Streamlining is one of the most frequently utilized visualization methods to analyze the flow structure of computational fluid dynamics (CFD) data. However, it is challenging to find a set of streamlines showing the most prominent flow across the entire flow field due to the heavy computation time required to generate bundles of streamlines. In this paper, we propose an efficient streamline generation method that removes several seed candidates that are predicted as less important using a 3D U-net based regression model. We employ 3D line integral convolution (LIC) volumes that depict the entire flow field for training data of the proposed learning model and evaluate our method using a real-world CFD data set. We find using our model that we can obtain quality of visualization results comparable to that of the ground truth even when more than 90% of the seed candidates are truncated while operating 6.6∼17.1 times faster than the competing method.INDEX TERMS deep regression network, dilated convolutional neural network, flow visualization, line integral convolution, streamline

show abstract

A rapid vortex identification method using fully convolutional segmentation network

Cited by 16 publications

References 22 publications

A Vortex Identification Method Based on Extreme Learning Machine

A Vortex Identification Method Based on Extreme Learning Machine

Exploratory Lagrangian-Based Particle Tracing Using Deep Learning

Deep Regression Network-Assisted Efficient Streamline Generation Method

Contact Info

Product

Resources

About