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

Differential evolution algorithm with variable crossover probability factor

A differential evolution algorithm and cross probability factor technology, applied in genetic models, genetic laws, etc., can solve problems such as differences and performance differences, and achieve the effect of reducing the number of iterations, computing time, and memory consumption.

Inactive Publication Date: 2018-04-13
SOUTHEAST UNIV
View PDF0 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For this reason, many experts have proposed a variety of mutation strategies, but different strategies have different performances when facing different problems, and the problems they are suitable for solving are also different.

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
  • Differential evolution algorithm with variable crossover probability factor
  • Differential evolution algorithm with variable crossover probability factor
  • Differential evolution algorithm with variable crossover probability factor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0078] Embodiment 1: This example compares the efficiency of two differential evolution algorithm cross factor determination schemes in the time modulation array antenna pattern optimization, one is the scheme proposed by the present invention, and the other is the traditional fixed cross factor scheme. The case compares which scheme requires fewer iterations to reduce the fitness value of the population below the threshold. In the case of a fixed objective function, the number of iterations required reflects the efficiency of numerical optimization.

[0079] Here, the optimized vector length J is 36, and the number of populations is N P The value is 4.0 times J, and the variation factor F is 0.6. In the traditional scheme, the crossover factor CR is set to 0.9. In the scheme proposed by the present invention, the low-end parameter CR of the crossover probability low and the high-end parameter CR up The values ​​are 0.1 and 0.9 respectively.

[0080] When the total number ...

Embodiment 2

[0081] Example 2: This example compares the efficiency of two differential evolution algorithm crossover factor determination schemes in the optimization of the time modulation array antenna pattern, one is the scheme proposed by the present invention, and the other is the linear increase in crossover probability in the literature Program:

[0082]

[0083] where CR min and CR max are the minimum and maximum values ​​of the crossover probability, g is the number of optimization iterations, and G is the total number of iterations of optimization iterations. The crossover probability in this scheme increases linearly with the number of iterations, from CR min increases all the way to CR max .

[0084] Here, the optimized vector length J is 36, and the number of populations is N P The value is 4.0 times J, and the variation factor F is 0.6. In the scheme proposed by the present invention, the low-end parameter CR of the crossover probability low and the high-end paramet...

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 a differential evolution algorithm with a variable crossover probability factor, comprising the following steps: (1) population initialization; (2) mutation operation; (3) crossover operation; (4) selection operator; (5) termination of iteration . The beneficial effects of the present invention are: the present invention proposes a differential evolution algorithm with a variable crossover probability factor, in the crossover link, according to the size of the fitness value of different individuals in the previous generation, different individuals are given different crossover probability factor values; embodiment It shows that, compared with the traditional DE algorithm, when using this algorithm for numerical optimization, the number of iterations required is significantly reduced, the optimal value we expect can be searched faster, and the calculation time and memory consumption are effectively reduced.

Description

technical field [0001] The invention relates to the technical field of numerical optimization, in particular to a differential evolution algorithm with variable crossover probability factors. Background technique [0002] Numerical optimization is an old and thorny problem, especially complex high-dimensional, multi-peak, multi-objective optimization problems. With the complexity and diversification of solving problems, the traditional deterministic optimization algorithm can no longer solve the problem well, so evolutionary algorithms such as differential evolution algorithm came into being. [0003] Differential Evolution (DE) algorithm is proposed by Rainer Storn and Kenneth Price in 1997, which is an optimization algorithm that uses floating-point vector encoding to perform random search in continuous space. Since the advent of the DE algorithm, it has attracted the attention of many experts and scholars at home and abroad because of its simplicity and high efficiency, ...

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): G06N3/12
CPCG06N3/126
Inventor 蒋忠进崔铁军陈阳阳
Owner SOUTHEAST UNIV
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