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

Variable-convexity roller type self-adaptive design method based on genetic algorithm

A technology of genetic algorithm and design method is applied in the field of adaptive design of variable crown roll shape based on genetic algorithm, which can solve the problem that the adjustment ability of CVC roll shape is reduced, it cannot meet production requirements, and the service life of variable crown roll shape is shortened. and other problems to achieve the effect of improving actual performance and life.

Pending Publication Date: 2020-01-14
HUBEI UNIV OF TECH
View PDF2 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The axial traversing distance of the CVC roll type has a linear relationship with the quadratic equivalent crown, but for different strip widths, especially narrow strips, the crown adjustment ability of the CVC roll type decreases, and cannot adapt to the same production line Production requirements for different strip widths
And compared with conventional rolls, the service life of variable crown rolls has a certain decrease. How to improve the service life of rolls under the premise of improving the crown adjustment ability of variable crown rolls is an important demand in metal rolling forming.

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
  • Variable-convexity roller type self-adaptive design method based on genetic algorithm
  • Variable-convexity roller type self-adaptive design method based on genetic algorithm
  • Variable-convexity roller type self-adaptive design method based on genetic algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0094] according to figure 1The shown algorithm flow designs the roll shape. First, the CVC roll shape is selected as the roll shape of the initial iteration, and the CVC roll shape coefficients are shown in Table 1. Set a certain floating range for the coefficient to increase the number of roll shapes.

[0095] Table 1 CVC roll shape coefficient table

[0096]

[0097] Let the population size be 800, randomly generate the initial iterative population r N×M = r 1 (i),r 2 (i),...r N (i). Calculate G 0 The fitness of each roll shape curve in , and the parameters in the fitness function are shown in Table 2.

[0098] Table 2 Design parameters of roll shape

[0099]

[0100] The genetic algorithm is used to process the initial discretized roll shape curve, and its parameter settings are shown in Table 3. The code length is selected from the roll shape curve design program library of the roll grinder, and the number of populations, crossover probability, mutation pr...

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 the technical field of roller type design, in particular to a variable-convexity roller type self-adaptive design method based on a genetic algorithm. The method comprises thefollowing steps: performing x-direction equidistant sampling on all roll curves in an initial roll curve population to generate an initial discretized roll curve; establishing a fitness function of the convexity control capability by taking the linearity of the convexity and the roll shifting amount as an index; establishing a fitness function of roller abrasion according to the abrasion characteristics of the hot rolling working roller; constructing a roller comprehensive fitness function according to the fitness function of the convexity control capability and the fitness function of the roller wear; and in combination with a roller comprehensive fitness function, performing iterative optimization on the initial discretized roller type curve by adopting a genetic algorithm, and taking the roller type curve obtained by iterative optimization as an output roller type curve. The roller type designed by the method can improve the convexity adjusting capacity and the abrasion resistanceof the roller, effectively prolong the service life of the roller and effectively improve the plate shape control capacity of the roller.

Description

technical field [0001] The invention relates to the technical field of roll profile design, in particular to a genetic algorithm-based self-adaptive design method for variable crown roll profiles. Background technique [0002] Roll profile curve is one of the important factors affecting sheet forming precision and surface quality, and the roll profile design of variable crown roll is a hot spot in roll analysis. Variable crown roll shape, that is, axial displacement variable crown roll shape, this roll shape can make the crown change continuously during the axial movement process, so as to improve the shape control performance. As a mature and applied roll type, the variable crown roll type has a long history of technical development. Among them, the CVC roll profile, as the most common variable crown roll profile, was invented by the German SMS company and was applied to domestic steel production lines as early as the 1980s. [0003] The axial traversing distance of the C...

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
IPC IPC(8): G06F30/17G06F30/20G06N3/12G06F113/22
CPCG06N3/126
Inventor 丁国龙邱兆祥汤明俊张力惟程铖廖小亮
Owner HUBEI 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