Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Real-time prediction method for aerodynamic performance parameters of automobile based on three-dimensional deep learning

A technology of aerodynamic performance and deep learning, applied in the field of aerodynamics and deep learning, can solve problems such as high-degree-of-freedom large-scale engineering problem dependence, computer performance requirements, and time-consuming problems, so as to speed up the design of aerodynamic layout and reduce R&D The effect of cycle and low cost

Pending Publication Date: 2021-10-15
DALIAN UNIV OF TECH
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Instead, it is the wind tunnel test, which can artificially design the flow field properties of the wind tunnel, control the test conditions and obtain relatively reliable results, but the test is difficult and expensive
The numerical simulation method is developed based on Computational Fluid Dynamics (CFD), which mainly uses computers to test the aerodynamic performance of cars under artificially set conditions. However, large-scale engineering problems with high degrees of freedom rely on supercomputers. Performance has high requirements and takes a lot of time

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
  • Real-time prediction method for aerodynamic performance parameters of automobile based on three-dimensional deep learning
  • Real-time prediction method for aerodynamic performance parameters of automobile based on three-dimensional deep learning
  • Real-time prediction method for aerodynamic performance parameters of automobile based on three-dimensional deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description These are some embodiments of the present invention. Those skilled in the art can also obtain other drawings based on these drawings without creative work.

[0025] A real-time prediction method of automobile aerodynamic performance parameters based on three-dimensional deep learning proposed by the present invention, such as figure 1 As shown, it specifically includes the following steps:

[0026] S1. Obtain the 3D digital model and point cloud data of the car body, and process the data; the specific process is as follows: use T-Splines to construct the car shape surface model, then extract the surface control points and output the 3D coordinates of each point...

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

The invention relates to a real-time prediction method for aerodynamic performance parameters of an automobile based on three-dimensional deep learning. The method comprises the following steps: constructing a three-dimensional model of an automobile body by using a T spline; simulating and calculating aerodynamic performance parameters of the model by using CFD software, and adding a wind speed label into three-dimensional point cloud data so as to construct a training data set; and carrying out adaptive modification based on a PointNet network, taking the processed point cloud data as the input of a deep neural network, adjusting training parameters, and carrying out prediction on the aerodynamic performance parameters of the automobile by using the trained deep neural network. According to the method, rapid real-time prediction of the aerodynamic performance parameters of the automobile is achieved, tedious CFD calculation is avoided through direct application of experimental data, and the method has great significance in promoting application of deep learning in aerodynamics.

Description

technical field [0001] The invention relates to the technical fields of aerodynamics and deep learning, in particular to a method for real-time prediction of automobile aerodynamic performance parameters based on three-dimensional deep learning. Background technique [0002] Automobile aerodynamic layout design is an important link in automobile design. By reducing the aerodynamic drag coefficient of the car, the aerodynamic performance of the car can be improved, which is of great significance to the energy saving and emission reduction of fuel vehicles and the increase of the mileage of electric vehicles. [0003] At present, the research on the aerodynamic performance of automobiles mainly adopts the method based on theoretical research and the combination of numerical analysis and experimental analysis. The main methods of test analysis are road test and automobile wind tunnel test. The test site for road test is scarce, the test cycle is long, and the time and capital ...

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): G06F30/15G06F30/27G06F30/28G06N3/04G06N3/08G06F113/08G06F119/14
CPCG06F30/15G06F30/27G06F30/28G06N3/04G06N3/08G06F2113/08G06F2119/14Y02T90/00
Inventor 祝雪峰张书生
Owner DALIAN UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com