Three-dimensional spatiotemporal wind field reconstruction based on physics-informed deep learning

2021 ◽  
Vol 300 ◽  
pp. 117390
Author(s):  
Jincheng Zhang ◽  
Xiaowei Zhao
Keyword(s):  
Deep Learning ◽  
Wind Field ◽  
Three Dimensional ◽  
Field Reconstruction

scholarly journals Real-time three dimensional wind field reconstruction from nacelle LiDAR measurements

2018 ◽  
Vol 1037 ◽  
pp. 032037
Author(s):  
F. Guillemin ◽  
H.-N. Nguyen ◽  
G. Sabiron ◽  
D. Di Domenico ◽  
M. Boquet
Keyword(s):  
Real Time ◽  
Wind Field ◽  
Three Dimensional ◽  
Field Reconstruction ◽  
Lidar Measurements

scholarly journals Three Dimensional Dynamic Model Based Wind Field Reconstruction from Lidar Data

2014 ◽  
Vol 524 ◽  
pp. 012005 ◽  
Author(s):  
Steffen Raach ◽  
David Schlipf ◽  
Florian Haizmann ◽  
Po Wen Cheng
Keyword(s):  
Dynamic Model ◽  
Wind Field ◽  
Three Dimensional ◽  
Lidar Data ◽  
Field Reconstruction ◽  
Model Based

scholarly journals Deep learning‐based carotid media‐adventitia and lumen‐intima boundary segmentation from three‐dimensional ultrasound images

2019 ◽  
Vol 46 (7) ◽  
pp. 3180-3193 ◽  
Author(s):  
Ran Zhou ◽  
Aaron Fenster ◽  
Yujiao Xia ◽  
J. David Spence ◽  
Mingyue Ding
Keyword(s):  
Deep Learning ◽  
Three Dimensional ◽  
Ultrasound Images

Dynamic simulation of wind field in three-dimensional display space considering particle swarm algorithm fuzzy logic

2021 ◽  
pp. 1-6
Author(s):  
Honglei Xu ◽  
Linhuan Wang
Keyword(s):  
Fuzzy Logic ◽  
Dynamic Simulation ◽  
Wind Field ◽  
Three Dimensional ◽  
Measurement Data ◽  
Particle Swarm ◽  
Particle Swarm Algorithm ◽  
Three Dimensional Display ◽  
Swarm Algorithm ◽  
Synchronous Measurement

In order to improve the accuracy of dynamic detection of wind field in the three-dimensional display space, system software is carried out on the actual scene and corresponding airborne radar observation information data, and the particle swarm algorithm fuzzy logic algorithm is introduced into the wind field dynamic simulation process in three-dimensional display space, to analyze the error of the filtering result in detail, to process the hurricane Lily Doppler radar measurement data with the optimal adaptive filtering according to the error data. The three-dimensional wind field synchronous measurement data obtained by filtering was compared with three-dimensional wind field synchronous measurement data of the GPS dropsonde in this experiment, the sea surface wind field measurement data of the multi-band microwave radiometer, and the wind field data at aircraft altitude.

scholarly journals Automated Segmentation of Infarct Lesions in T1-Weighted MRI Scans Using Variational Mode Decomposition and Deep Learning

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 1952
Author(s):  
May Phu Paing ◽  
Supan Tungjitkusolmun ◽  
Toan Huy Bui ◽  
Sarinporn Visitsattapongse ◽  
Chuchart Pintavirooj
Keyword(s):  
Deep Learning ◽  
Brain Infarction ◽  
Three Dimensional ◽  
Dice Similarity Coefficient ◽  
Automated Segmentation ◽  
Variational Mode Decomposition ◽  
Brain Scans ◽  
Automated Method ◽  
Mode Decomposition ◽  
Segmentation Task

Automated segmentation methods are critical for early detection, prompt actions, and immediate treatments in reducing disability and death risks of brain infarction. This paper aims to develop a fully automated method to segment the infarct lesions from T1-weighted brain scans. As a key novelty, the proposed method combines variational mode decomposition and deep learning-based segmentation to take advantages of both methods and provide better results. There are three main technical contributions in this paper. First, variational mode decomposition is applied as a pre-processing to discriminate the infarct lesions from unwanted non-infarct tissues. Second, overlapped patches strategy is proposed to reduce the workload of the deep-learning-based segmentation task. Finally, a three-dimensional U-Net model is developed to perform patch-wise segmentation of infarct lesions. A total of 239 brain scans from a public dataset is utilized to develop and evaluate the proposed method. Empirical results reveal that the proposed automated segmentation can provide promising performances with an average dice similarity coefficient (DSC) of 0.6684, intersection over union (IoU) of 0.5022, and average symmetric surface distance (ASSD) of 0.3932, respectively.

scholarly journals Multi-Dimensional Underwater Point Cloud Detection Based on Deep Learning

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 884
Author(s):  
Chia-Ming Tsai ◽  
Yi-Horng Lai ◽  
Yung-Da Sun ◽  
Yu-Jen Chung ◽  
Jau-Woei Perng
Keyword(s):  
Deep Learning ◽  
Point Cloud ◽  
Three Dimensional ◽  
Point Clouds ◽  
Training Data ◽  
Network Architectures ◽  
Point Cloud Data ◽  
Data Types ◽  
Raw Data ◽  
Cloud Data

Numerous sensors can obtain images or point cloud data on land, however, the rapid attenuation of electromagnetic signals and the lack of light in water have been observed to restrict sensing functions. This study expands the utilization of two- and three-dimensional detection technologies in underwater applications to detect abandoned tires. A three-dimensional acoustic sensor, the BV5000, is used in this study to collect underwater point cloud data. Some pre-processing steps are proposed to remove noise and the seabed from raw data. Point clouds are then processed to obtain two data types: a 2D image and a 3D point cloud. Deep learning methods with different dimensions are used to train the models. In the two-dimensional method, the point cloud is transferred into a bird’s eye view image. The Faster R-CNN and YOLOv3 network architectures are used to detect tires. Meanwhile, in the three-dimensional method, the point cloud associated with a tire is cut out from the raw data and is used as training data. The PointNet and PointConv network architectures are then used for tire classification. The results show that both approaches provide good accuracy.

scholarly journals Engineering Comprehensive Model of Complex Wind Fields for Flight Simulation

Aerospace ◽  
2021 ◽  
Vol 8 (6) ◽  
pp. 145
Author(s):  
Jianwei Chen ◽  
Liangming Wang ◽  
Jian Fu ◽  
Zhiwei Yang
Keyword(s):  
Wind Field ◽  
Three Dimensional ◽  
Great Influence ◽  
Spatial Location ◽  
Flight Simulation ◽  
Comprehensive Model ◽  
Flight Trajectory ◽  
Wind Fields ◽  
Wind Field Simulation ◽  
Low Level Jet

A complex wind field refers to the typical atmospheric disturbance phenomena existing in nature that have a great influence on the flight of aircrafts. Aimed at the issues involving large volume of data, complex computations and a single model in the current wind field simulation approaches for flight environments, based on the essential principles of fluid mechanics, in this paper, wind field models for two kinds of wind shear such as micro-downburst and low-level jet plus three-dimensional atmospheric turbulence are established. The validity of the models is verified by comparing the simulation results from existing wind field models and the measured data. Based on the principle of vector superposition, three wind field models are combined in the ground coordinate system, and a comprehensive model of complex wind fields is established with spatial location as the input and wind velocity as the output. The model is applied to the simulated flight of a rocket projectile, and the change in the rocket projectile’s flight attitude and flight trajectory under different wind fields is analyzed. The results indicate that the comprehensive model established herein can reasonably and efficiently reflect the influence of various complex wind field environments on the flight process of aircrafts, and that the model is simple, extensible, and convenient to use.

Sign in / Sign up

Export Citation Format

Share Document