Fluid animation accelerated generation method based on data driving

A data-driven, fluid technology, applied in the field of projection steps, can solve problems such as inapplicability, and achieve the effect of ensuring accuracy, small solution errors, and avoiding iterative calculations

Inactive Publication Date: 2016-10-12
SHANGHAI JIAO TONG UNIV
View PDF2 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method is not suitable for fluid simulation in the Euler method

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Fluid animation accelerated generation method based on data driving
  • Fluid animation accelerated generation method based on data driving
  • Fluid animation accelerated generation method based on data driving

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] This embodiment shows an embodiment of an artificial neural network learned from training samples and performing fast calculation of projection steps. Such as figure 1 As shown, this embodiment includes the following steps:

[0042] Step 1, discretely solve the Navier-Stokes equation, and collect the training data needed to train the artificial neural network in the next step:

[0043] 1.1, according to the sequence of convection step, external force step, and diffusion step, the equations are discretized and solved.

[0044] 1.2, the projection step relies on the normal numerical calculation solution to solve. In each grid of each frame, the input vector and output vector before and after the projection step are collected as training samples.

[0045] Step 2, design the structure of artificial neural network, including input layer, output layer, hidden layer. And adjust the number of layers in the hidden layer and the number of hidden nodes in each layer. This emb...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

A data-driven fluid animation acceleration generation method, using the artificial neural network after the training sample training as the solver, the solution of the projection step in the Euler method fluid simulation process is very fast, and can maintain a relatively fast solution while maintaining The small solution error ensures the accuracy of the solution results. The present invention uses the training data calculated before and after the projection step, and adjusts the weights of the transmission nodes of the artificial neural network through the training of the artificial neural network to directly obtain the final calculation model, completely avoiding the original time-consuming value calculation process of the projection step. The present invention is applicable to Euler's method for simulating fluid animation, and greatly accelerates the calculation of the solution projection step.

Description

technical field [0001] The invention relates to a technology in the field of image processing, specifically a method for greatly accelerating the most time-consuming projection step in the process of generating fluid animation by Euler's method with the help of a large amount of training data and artificial neural network. Background technique [0002] Physics-based fluid simulation is one of the important research directions in computer graphics. The physics-based fluid simulation process requires solving the Navier‐Stokes equations (NS equations). But because this equation is a nonlinear partial differential equation, Lagrangian method and Euler method are respectively used in the discretization solution of NS equation. In the field of high-precision fluid simulation, the Euler method is widely used. However, the Euler method needs to solve the Poisson equation to obtain the pressure in the projection step, which consumes a lot of computing resources. [0003] In recent...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T13/00
CPCG06T13/00
Inventor 杨成杨旭波肖祥云
Owner SHANGHAI JIAO TONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap