Coachbuilt body combination property index modelling approach based on support vector machine

A support vector machine and comprehensive performance technology, applied in the field of car body comprehensive performance index modeling, can solve problems such as mathematical model precision optimization design

Inactive Publication Date: 2008-08-13
SHANGHAI JIAO TONG UNIV
View PDF0 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] After searching the existing technical literature, it was found that Wang Hailiang, Lin Zhongqin, and Jin Xianlong published an article "Optimized Design of Crashworthiness of Thin-walled Components Based on Response Surface Model" in "Journal of Applied Mechanics" 2003, (3): 61-66 In this paper, the second-order polynomial model is used to establish the mathematical model of the crashworthiness index (crash index, maximum impact force, and average impact force) of the body structure, and the variance analysis is only used as a verification method in the modeling process, and no additional parameters are included in the design space. Select a certain number of random and evenly distributed samples for response prediction test, so it cannot be considered that the established mathematical model has sufficient accuracy for subsequent optimization design

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
  • Coachbuilt body combination property index modelling approach based on support vector machine
  • Coachbuilt body combination property index modelling approach based on support vector machine
  • Coachbuilt body combination property index modelling approach based on support vector machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The embodiments of the present invention are described in detail below in conjunction with the accompanying drawings: this embodiment is implemented on the premise of the technical solution of the present invention, and detailed implementation methods and specific operating procedures are provided, but the protection scope of the present invention is not limited to the following the described embodiment.

[0031] As shown in Figure 1, this embodiment includes the following steps:

[0032] Step 1. Determine the design variables for body structure optimization: select the plate thickness of 36 parts (15 pairs of symmetrical parts and 6 asymmetrical parts) of the front structure of a certain type of car body and the yield limits of the two materials as design variables, a total of 23 design variables, as shown in Table 1. During the frontal collision of a car, the performance constraints are peak acceleration, peak collision force, energy absorption, and maximum displacem...

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 present invention provides an actuarial modeling method based on the car body combination property index of support vector machine, belonging to auto structure optimization design field, including step 1, selecting parts as design object, and determining thickness of parts, material parameter as design variable; step 2, adopting testing design method to generate design matrix according to the design variable determined by step 1; step 3, processing finite element simulation testing design according to the design matrix, extracting structural performance index value to complete the establishment of the training sample; step 4, training sample by supporting vector machine method, establishing combination property index mathematic model; step 5, verifying the established combination property index mathematic model by checking index; step 6, establishing adaptive process after verifying the high precision combination property index mathematic model. The invention is fit for nonlinear response index mathematical modeling having multiple variables, high structural performance, having high precision of the model prediction, high efficiency of modeling, high feasibility of optimum design.

Description

technical field [0001] The invention relates to a design method in the field of automobile technology, in particular to a method for modeling comprehensive performance indexes of a car body based on a support vector machine. Background technique [0002] With the rapid development of the automobile industry, the optimization design technology of the body structure has been gradually applied, so that the body structure has the best comprehensive performance and can reduce its own weight as much as possible. In the optimization design modeling process of car body structure, it is necessary to establish a mathematical relationship model between various comprehensive performance indicators and design variables, and car collision is a transient, large deformation, highly nonlinear physical process, including collision force, acceleration, The crashworthiness safety performance indicators including structural deformation and energy absorption have strong nonlinear characteristics....

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): G06F17/50
Inventor 朱平张宇陈关龙郭永进余海东潘峰
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