Unlock instant, AI-driven research and patent intelligence for your innovation.

Visualization system for identifying an evolutionary algorithm parameterization effect

An evolutionary algorithm and parameterization technology, applied in the field of visualization systems, can solve the problems of not systematically considering the parameterization effect, unclear parameter values ​​of the evolutionary algorithm, unfavorable evolutionary algorithm potential, etc., so as to overcome the uncertainty of parameters and reduce blindness. performance, improve the effect of optimization

Active Publication Date: 2020-01-07
GUANGDONG UNIV OF TECH
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005]Through extensive literature research, it is found that most people do not systematically consider the influence of parameterization effects on algorithm performance when using evolutionary algorithms, but only through simple trial calculations To confirm whether the parameter setting is reasonable, or directly follow the recommended values ​​in other literatures, these methods are not conducive to fully exploiting the potential of the evolutionary algorithm
In other words, when solving specific problems, most people do not know whether the parameter values ​​of the evolutionary algorithm are reasonable, and thus cannot determine whether the obtained solution is close enough to the theoretical optimal solution of the problem to be solved

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
  • Visualization system for identifying an evolutionary algorithm parameterization effect
  • Visualization system for identifying an evolutionary algorithm parameterization effect
  • Visualization system for identifying an evolutionary algorithm parameterization effect

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] Such as figure 1 as well as figure 2 As shown, a visualization system for identifying parametric effects of evolutionary algorithms, including a numerical calculation module, a graphic configuration module, a drawing parameter preprocessing module, and a graphic generation module;

[0033] The numerical calculation module is used to select the evolutionary algorithm and the problem to be solved, to construct several sets of value combinations of the parameters of the evolutionary algorithm, to set the value of each set of parameters and perform independent optimization calculations, and to evaluate the optimization of each set of parameters Effect, send the data to the drawing parameter preprocessing module;

[0034] The graphic configuration module is used to configure the color options of each layer of the compass diagram and the color saturation and filling style of a ring in the compass diagram corresponding to the value of each parameter, and send the data to the...

Embodiment 2

[0047] Such as figure 1 , figure 2 as well as image 3 As shown, in this embodiment, the classic second-generation non-dominated sorting genetic algorithm (NSGA-II) in the evolutionary algorithm is used as an example to solve the problem of pipe diameter optimization design of the water supply pipe network system, including the following steps:

[0048] Step 1: Configure the parameters of NSGA-II and obtain the optimization results. NSGA-II mainly has 5 parameters, choose 2 sampling points for each parameter, then there are 2 5 = 32 different parameter combinations. First, set the specific values ​​of each parameter of NSGA-II in the "Numerical Calculation Module". For each parameter combination, the optimization calculation program was run independently 100 times, and the above calculation results were summarized to obtain 32 groups of approximate optimal solutions for the optimal design problem of the water supply pipe network system diameter. Then, the number of times...

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 visualization system for identifying an evolutionary algorithm parameterization effect. The visualization system comprises a numerical calculation module, a graph configuration module, a drawing parameter preprocessing module and a graph generation module, according to the method, the parameterization effect of a certain evolutionary algorithm when a specific problem issolved can be visually recognized, and the optimal parameter combination for the problem is found. The value of the invention is to provide the system analysis method for effectively overcoming the parameter uncertainty of the evolutionary algorithm, so that the blindness when the evolutionary algorithm is applied to solve a specific problem is reduced, the optimization effect of the evolutionaryalgorithm is improved, and the probability of obtaining a globally optimal solution closer to a target problem is improved in limited time.

Description

technical field [0001] The present invention relates to the field of computers, and more particularly, to a visualization system for identifying parameterized effects of evolutionary algorithms. Background technique [0002] Evolutionary algorithm is a kind of optimization method based on the idea of ​​"natural selection and survival of the fittest" in Darwin's theory of evolution. Its principle is to simulate the process of finding the optimal solution of the problem to be solved as the evolution process of natural organisms through a specific coding method, that is, to obtain the solution of the problem to be solved in an iterative manner through operations such as selection, crossover, and mutation at the chromosome level. near optimal solution. [0003] Today, evolutionary algorithms are widely used in various fields, such as signal processing, image recognition, production scheduling, automatic control, mechanical design, and water resource management. The optimizatio...

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): G06N3/12G06T11/20G06T11/40
CPCG06N3/126G06T11/203G06T11/40
Inventor 王琦王礼炳文豪黄稳周倩倩王志红
Owner GUANGDONG UNIV OF TECH