基于适应度指导交配限制策略的重组算子与多目标优化研究

汪禹宏; 张屹

doi:10.12263/DZXB.20210048

您当前的位置：

首页 >

文章列表页 >

基于适应度指导交配限制策略的重组算子与多目标优化研究

学术论文 | 更新时间：2025-12-11

- 基于适应度指导交配限制策略的重组算子与多目标优化研究
- Research on Recombination Operator and Multi-Objective Optimization Based on Fitness Guided Mating Restriction Strategy
- 电子学报 2022年50卷第3期页码：710-717
- 作者机构：
  
  常州大学机械与轨道交通学院，江苏常州 213164
- 作者简介：
  
  [ "汪禹宏男，1996年7月生，浙江金华人，2019年获得内蒙古科技大学机械设计制造及其自动化工学学士学位，现为常州大机械设计制造及其自动化在读硕士研究生，研究方向为多目标优化算法.E-mail:2458651528@qq.com" ]
  [ "张屹（通讯作者）男，1976年12月生，甘肃兰州人，博士、教授、博士生导师、国家自然基金委机械学科评审专家.分别于2000年、2005年在中国科学技术大学获工学学士学位和工学博士；2006年至2008年在中国科学技术大学工程学院力学博士后流动站从事博士后研究，主要研究方向为机电系统现在设计方案、智能计算等." ]
- 基金信息：
  
  国家自然科学基金(51875053);科技部重点研发计划项目(2018YFC1903101)
- DOI：10.12263/DZXB.20210048
  中图分类号： TP18
- 收稿：2020-12-31，
  
  修回：2021-08-13，
  
  纸质出版：2022-03-25
- 稿件说明：
移动端阅览
汪禹宏,张屹.基于适应度指导交配限制策略的重组算子与多目标优化研究[J].电子学报,2022,50(03):710-717.

WANG Yu-hong,ZHANG Yi.Research on Recombination Operator and Multi-Objective Optimization Based on Fitness Guided Mating Restriction Strategy[J].ACTA ELECTRONICA SINICA,2022,50(03):710-717.
汪禹宏,张屹.基于适应度指导交配限制策略的重组算子与多目标优化研究[J].电子学报,2022,50(03):710-717. DOI： 10.12263/DZXB.20210048.

WANG Yu-hong,ZHANG Yi.Research on Recombination Operator and Multi-Objective Optimization Based on Fitness Guided Mating Restriction Strategy[J].ACTA ELECTRONICA SINICA,2022,50(03):710-717. DOI： 10.12263/DZXB.20210048.

摘要

本文提出了一种基于K-means聚类适应度指导交配限制的多目标优化算法（K-means clustering-based Fitness Guided mating restriction multi-objective Evolutionary Algorithm，KFGEA）.在该算法的迭代过程中，利用K-means聚类算法从全局角度提取种群结构化信息.基于聚类所得的全局信息，本文围绕个体局部信息设计了一种适应度指导交配限制策略去完成全局与局部信息的融合.该策略根据适应度值这一确定性信息来判断个体质量，对非支配解进行近邻重组，对支配解进行全局勘探，去维护算法搜索过程中开采和勘探的平衡.将KFGEA与多种主流的多目标进化算法进行试验对比研究与参数灵敏度分析的结果表明，KFGEA在求解具有复杂特性的多目标优化问题时优势明显，该策略可以有效提高多目标进化算法的性能.

Abstract

This paper proposes a multi-objective evolutionary algorithm with clustering based fitness guided mating restriction strategy (KFGEA). In the iteration process of this algorithm

K-means clustering algorithm is used to extract population structure information from a global perspective.Based on the global information obtained by clustering

this paper designs a fitness-guided mating restriction strategy around individual local information to complete the fusion of global and local information.This strategy judges the individual quality based on the deterministic information of fitness value

recombines the non-dominant solution with its neighbors

explores the dominant solution globally

and maintains the balance between exploitation and exploration during the algorithm search process.Compared with other mainstream multi-objective evolutionary algorithms

KFGEA has obvious advantages in solving multi-objective optimization problems with complex characteristics. The results show that this strategy can effectively improve the performance of multi-objective evolutionary algorithm.

关键词

Keywords

references

张虎 . 基于聚类的多目标进化算法重组算子研究 [D]. 哈尔滨 : 哈尔滨工业大学 , 2019 .

ZHANG Hu . Clustering-Based Reproduction Operators for Multiobjective Evolutionary Algorithms [D]. Harbin : Harbin Institute of Technology , 2019 . ( in Chinese)

ZHANG Qingfu , ZHOU Aimin , et al . RM-MEDA: A regularity model-based multiobjective estimation of distribution algorithm [J]. Evolutionary Computation IEEE Transactions on , 2008 , 12 ( 1 ): 41 ‑ 63 .

周爱民 , 张青富 , 张桂戌 . 一种基于混合高斯模型的多目标进化算法 [J]. 软件学报 , 2014 , 25 ( 05 ): 913 ‑ 928 .

ZHOU Ai-min , ZHANG Qing-fu , ZHANG Gui-xu . Multiobjective evolutionary algorithm based on mixture Gaussian models [J]. Journal of Software , 2014 , 25 ( 05 ): 913 ‑ 928 . (in Chinese)

BUENO M L P , OLIVEIRA G M B . A dynamic multi-objective evolutionary algorithm for multicast routing problem [C]// Proceedings of the 25th IEEE International Conference on Tools with Artificial Intelligence . New York, USA : IEEE , 2013 : 344 ‑ 350 .

GAO J , FANG L , WANG J . A weight-based multiobjective immune algorithm: WBMOIA [J]. Engineering Optimization , 2010 , 42 ( 8 ): 719 ‑ 745 .

ISHIBUCHI H , NARUKAWA K . An empirical study on similarity-based mating for evolutionary multiobjective combinatorial optimization [J]. European Journal of Operational Research , 2008 , 188 ( 1 ): 57 ‑ 75 .

YAOCHU JIN , SENDHOFF B . Connectedness, regularity and the success of local search in evolutionary multi-objective optimization [C]// Proceedings of the 2003 IEEE Congress on Evolutionary Computation . New York, USA : IEEE , 2003 : 1910 ‑ 1917 .

Arnaldo Pérez Castao . Clustering & multi-objective clustering [M]//. Practical Artificial Intelligence . Berlin : Springer , 2018 : 479 ‑ 507

李欣 . 基于聚类的多目标演化算法交配限制策略研究 [D]. 哈尔滨 : 哈尔滨工业大学 , 2019 .

LI Xin . Study of Clustering-Based Mating Restriction Strategies for Multiobjective Evolutionary Algorithms [D]. Harbin : Harbin Institute of Technology , 2019 . ( in Chinese)

ZHANG H , ZHOU A , SONG S , et al . A self-organizing multiobjective evolutionary algorithm [J]. IEEE Transactions on Evolutionary Computation , 2016 , 20 ( 5 ): 792 ‑ 806 .

ZHANG H , ZHANG X , SONG S , et al . An affinity propagation-based multiobjective evolutionary algorithm for selecting optimal aiming points of missiles [J]. Soft Computing-A Fusion of Foundations, Methodologies and Applications , 2017 , 21 ( 11 ): 3013 ‑ 3031 .

LI X , SONG S , ZHANG H . Evolutionary multi-objective optimization with clustering-based self-adaptive mating restriction strategy [J]. Soft Computing , 2018 , 23 ( 33 ): 3 ‑ 25 .

WANG S , ZHANG H , ZHANG Y , et al . A spectral clustering-based multi-source mating selection strategy in evolutionary multi-objective optimization [J]. IEEE Access , 2019 , 7 ( 131 ): 851 ‑ 864 .

LI X , ZHANG H , SONG S . A self-adaptive mating restriction strategy based on survival length for evolutionary multiobjective optimization [J]. Swarm & Evolutionary Computation , 2018 , 43 : 31 ‑ 49 .

付宁 , 乔立岩 , 彭喜元 . 基于改进K-means聚类和霍夫变换的稀疏源混合矩阵盲估计算法 [J]. 电子学报 , 2009 , 37( 0 z 1 ): 92 ‑ 96 .

FU Ning , QIAO Li-yan , PENG Xi-yuan . Blind recovery of mixing matrix with sparse sources based on improved K-means clustering and hough transform [J]. Acta Electronica Sinica , 2009 , 37( 0 z 1 ): 92 ‑ 96 . (in Chinese)

张秀杰 , 李欣 , 张虎 , 等 . 基于自适应配对控制的多目标演化算法 [J]. 控制与决策 , 2018 , 33 ( 3 ): 392 ‑ 402 .

ZHANG Xiu-jie , LI Xin , ZHANG Hu , et al . Adaptive mating control based multi-objective evolutionary algorithm [J]. Control and Decision , 2018 , 33 ( 3 ): 392 ‑ 402 . (in Chinese)

ZITZLER E , LAUMANNS M , THIELE L . SPEA2: Improving the strength pareto evolutionary algorithm [J]. Technical Report Gloriastrasse , 2001 , 3242 ( 103 ) : 95 ‑ 100 .

LI H , ZHANG Q . Multi-objective optimization problems with complicated pareto sets, MOEA/D and NSGA-II [J]. IEEE Transactions on Evolutionary Computation , 2009 , 13 ( 2 ): 284 ‑ 302 .

尚荣华 , 胡朝旭 , 焦李成 , 等 . 多目标优化算法在多分类中的应用研究 [J]. 电子学报 , 2012 , 40 ( 11 ): 2264 ‑ 2269 .

SHANG Rong-hua , HU Chao-xu , JIAO Li-cheng , et al . Research of multi-objective optimization algorithms application in multi-class classification [J]. Acta Electronica Sinica , 2012 , 40 ( 11 ): 2264 ‑ 2269 . (in Chinese)

张屹 , 余振 , 李子木 , 等 . 基于模糊C均值聚类的锦标赛选择机制与多目标优化研究 [J]. 电子学报 , 2017 , 45 ( 011 ): 2677 ‑ 2684 .

ZHANG Yi , YU Zhen , LI Zi-mu , et al . Tournament selection for multi-objective optimization based on fuzzy c-means clustering method [J]. Acta Electronica Sinica , 2017 , 45 ( 011 ): 2677 ‑ 2684 . (in Chinese)

张屹 , 万兴余 , 郑小东 , 等 . 基于正交设计的元胞多目标遗传算法 [J]. 电子学报 , 2016 , 44 ( 01 ): 87 ‑ 94 .

ZHANG Yi , WAN Xing-yu , ZHENG Xiao-dong , et al . Cellular genetic algorithm for multi-objective optimization based on orthogonal design [J]. Acta Electronica Sinica , 2016 , 44 ( 01 ): 87 ‑ 94 . (in Chinese)

Michael Emmerich Nicola Beume Boris Naujoks . An EMO algorithm using the hypervolume measure as selection criterion [C]// Evolutionary Multi-Criterion Optimization . Berlin : Springer , 2005 : 62 ‑ 76 .

DEB K , PRATAP A , AGARWAL S , et al . A fast and elitist multi-objective genetic algorithm: NSGA-II [J]. IEEE Transactions on Evolutionary Computation , 2002 , 6 ( 2 ): 182 ‑ 197 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于多源交配选择策略的重组算子与多目标优化研究

基于生态种群捕获竞争模型的多目标Memetic优化算法

带特征选择的综合因果多目标反事实解释方法

车联网中基于位置信息映射和相关性评估的进化多任务优化算法

区域和邻域级信息相结合的加强型PFCM含噪图像分割算法