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

Engine hood lightweight design method based on radial basis function neural network approximation model

A technology based on neural network and lightweight design, which is applied in the field of lightweight design of engine hood based on RBF approximate model of radial basis neural network, can solve the problems of high cost, long calculation time, limited effect, etc., and achieves lightweight design. Effect

Active Publication Date: 2020-10-20
CHINA FIRST AUTOMOBILE
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] For the automobile body, most parts adopt sheet metal structure, and due to the limitation of space layout and function, the effect of light weight and weight reduction through structural optimization is limited. It is very meaningful for the lightweight of the car body. The material thickness of the sheet metal parts can generally be changed in a wide range. For the assembly of multiple parts, it may be necessary to calculate the performance of various material thickness combinations Thousands of calculations are performed, the calculation time is long and the cost is high

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
  • Engine hood lightweight design method based on radial basis function neural network approximation model
  • Engine hood lightweight design method based on radial basis function neural network approximation model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0065] refer to figure 1 , the engine hood lightweight design method based on radial basis neural network RBF approximation model of the present invention, comprises the steps:

[0066] S1: Establish the finite element model of the sheet metal parts of the hood assembly, and complete the calculation of the finite element model boundary conditions and load settings for the four analysis conditions of the hood modal, lateral stiffness, intermediate constraint torsional stiffness, and side constraint torsional stiffness.

[0067] S2: Select the material thickness of each sheet metal part of the engine hood as a design variable, and set the variable range as a discrete variable according to the actual variable range of material thickness of each sheet metal part.

[0068] S3: Use the orthogonal matrix method to select the variable test matrix, output the finite element model corresponding to each variable under the test matrix, and analyze and calculate the modal, lateral stiffnes...

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 discloses an engine hood lightweight design method based on a radial basis function neural network approximation model, and the method comprises the steps: carrying out the multi-objective lightweight optimization analysis based on the RBF neural network approximation model: building an engine hood assembly finite element model, completing the modal and rigidity analysis of an enginehood, establishing an approximation model based on the radial basis function (RBF) neural network, and performing multi-objective optimization according to the approximation model; and performing engine hood performance simulation verification and optimization: establishing an engine hood full interior refined model, completing engine hood closing transient strength analysis, and optimizing a local structure according to a strength analysis result. According to the invention, multi-objective lightweight optimization analysis is carried out on the engine hood based on the radial basis functionneural network approximation model, the optimal lightweight scheme is obtained, performance simulation verification and optimization are carried out subsequently through a refined model, the performance simulation precision is guaranteed while the optimization efficiency is guaranteed, and the optimal combination of the thickness of a sheet metal part of an engine hood is achieved.

Description

technical field [0001] The invention relates to a lightweight design method for an engine hood, in particular to a lightweight design method for an engine hood based on a radial basis neural network RBF approximate model. Background technique [0002] With the increasingly serious environmental pollution and stricter emission regulations for vehicles, this requires vehicles to develop in the direction of energy-saving and new energy vehicles. Whether it is traditional fuel vehicles or new energy vehicles, lightweight is an important way to solve this problem one. With the help of computer simulation technology, product development efficiency can be effectively improved, product development cycle can be shortened, and the purpose of lightweight design can be achieved. [0003] For the automobile body, most parts adopt sheet metal structure, and due to the limitation of space layout and function, the effect of light weight and weight reduction through structural optimization ...

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): G06F30/15G06F30/23G06N3/08
CPCG06F30/15G06F30/23G06N3/08Y02T10/40
Inventor 肖永富曹正林张雨于保君马明辉李鼎杨少明刘启龙于礼艳
Owner CHINA FIRST AUTOMOBILE
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