作者：
Gu, ShushengWang, JingyuLi, GuanxiongDeng, XiaogangSichuan University
College of Computer Science The National key laboratory of Fundamental Algorithms and Models for Engineering Simulation 610065 China Sichuan University
School of Aeronautics and Astronautics The National key laboratory of Fundamental Algorithms and Models for Engineering Simulation 610065 China Sichuan University
National key laboratory of Fundamental Algorithms and Models for Engineering Simulation 610065 China
Particle Image Velocimetry (PIV) is a crucial technique in experimental fluid dynamics for non-invasively measuring the velocity components of flow fields. Deep learning methods applied to PIV for velocity field estim...
详细信息
Particle Image Velocimetry (PIV) is a crucial technique in experimental fluid dynamics for non-invasively measuring the velocity components of flow fields. Deep learning methods applied to PIV for velocity field estimation are primarily derived from computer vision. However, these methods often fail to account for the distinctive characteristics of fluid dynamics, such as the very small scales of objects and displacements relative to pixel resolution, high-density particle distributions, complex and irregular motion patterns. As demonstrated in this work, these approaches encounter three main challenges: (i) failure to accurately estimate the motion for very small particles and displacements;(ii) significant computational discrepancies with high-density particle distributions;and (iii) considerable inaccuracies in the analysis of complex flow fields. To address these issues, we propose a novel convolutional neural network, named Multi-Scale Feature Recurrent All-Pairs Field Transforms (MSF-RAFT). Our approach involves: (1) developing a highresolution multi-scale feature extraction network;(2) integrating an innovative residual block to improve the network;and (3) creating a multi-scale feature correction module that constructs a four-layer correlation pyramid. The proposed network has been validated on various datasets and experimental images. MSF-RAFT exhibits superior performance, particularly with high-density small particle images, achieving a significant reduction in estimation error and accurately capturing small vortex details. Comparative analyses with benchmark models demonstrate that MSF-RAFT achieves up to a 33% reduction in estimation error compared to previous best models on complex datasets and provides a flow field estimation that more accurately represents the fluid dynamics around the nacelle. Additionally, evaluations of model size, runtime, and memory consumption demonstrate that MSF-RAFT is highly efficient, making it well-suited to meet the indu
Traditional text-based person ReID assumes that person descriptions from witnesses are complete and provided at once. However, in real-world scenarios, such descriptions are often partial or vague. To address this lim...
With the widespread application of numerical simulation in aeroengine, it is crucial to automatically and efficiently generate structured grids for rotating components. Therefore, a comprehensive structured grid autom...
详细信息
With the widespread application of numerical simulation in aeroengine, it is crucial to automatically and efficiently generate structured grids for rotating components. Therefore, a comprehensive structured grid autom...
详细信息
In this study, we present a novel computational framework that integrates the finite volume method with graph neural networks to address the challenges in Physics-Informed Neural Networks(PINNs). Our approach leverage...
详细信息
Solar power is a vital energy source for stratospheric airships, and the layout of solar cells significantly influences both their performance and the airship's parameters. A numerical discretization method is emp...
详细信息
In this study, we present a novel computational framework that integrates the finite volume method with graph neural networks to address the challenges in Physics-Informed Neural Networks(PINNs). Our approach leverage...
详细信息
Advances in deep learning have enabled physics-informed neural networks to solve partial differential equations. Numerical differentiation using the finite-difference (FD) method is efficient in physics-constrained de...
详细信息
Outlier detection is an important part of the process of carrying out data mining and analysis and has been applied to many fields. Existing methods are typically anchored in a single-sample processing paradigm, where...
详细信息
In recent years, neural network technology has made significant progress in the field of unsteady flow field prediction, leading to the development of many innovative methods. However, deep learning-based unsteady flo...
详细信息
In recent years, neural network technology has made significant progress in the field of unsteady flow field prediction, leading to the development of many innovative methods. However, deep learning-based unsteady flow field prediction techniques typically rely on autoregressive models, which inevitably face the issue of error accumulation. Existing solutions often suffer from challenges such as complex hyperparameter configurations and reduced training efficiency. To address these issues, this study makes the following contributions: (1) A novel training method is proposed to enhance model convergence by refining the training strategies employed. This approach achieves improved performance without necessitating complex hyperparameter configurations. (2) An innovative curriculum learning-based timestep reset strategy is introduced. This strategy further improves the convergence of neural networks and enhances prediction accuracy. A detailed comparative study was conducted on different training methods within the architecture of convolutional neural networks. Experimental results show that the proposed training strategy significantly improves prediction accuracy, with an improvement of up to an order of magnitude. Moreover, even when the training set spans only 600 timesteps, the model remains stable when predicting up to 9000 timesteps. Finally, our method also demonstrates high efficiency in terms of training time.
暂无评论