.png){kind=icon}
返回
Dual-stage and dual-population cooperative evolutionary algorithm for solving constrained multiobjective problems
.png){kind=icon}
PRE
AI
DOI：10.1016/j.asoc.2024.111703.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
During the search process, the characteristics of the feasible regions encountered by the population continually change in Constrained Multiobjective Optimization Problems (CMOPs). This variability poses a challenge for traditional evolutionary algorithms, which often struggle to adapt to the diverse problem characteristics of the encountered feasible regions. To overcome this limitation, we propose a Dual -Stage and Dual -Population Cooperative Evolutionary Algorithm (DDCEA) to address CMOPs characterized by diverse feasible regions. DDCEA employs a dual -stage mechanism to adapt the offspring generation strategy and establishes two distinct populations to evaluate offspring using constraint -sensitive and constraint -free strategies. Comparative analyses reveal that DDCEA surpasses chosen state-of-the-art CMOEAs in adapting to the changing feasible regions and then approximating the constrained Pareto fronts.
Keyword:
Constrained multiobjective optimization
problems (CMOPs)
Cooperation
Evolutionary algorithm
Reproduction and evaluation strategies
期刊
IF:
6.6
论文数:
1.4W
被引数:
4.8W
机构
引用论文
PlatEMO: A MATLAB Platform for Evolutionary Multi-Objective OptimizationPlatEMO: 用于进化多目标优化的MATLAB平台
OAAI
OAAI分享收藏A decomposition-based constrained multi-objective evolutionary algorithm with a local infeasibility utilization mechanism for UAV path planning基于局部不可行性利用机制的分解约束多目标进化算法的无人机航迹规划
PREAI
分享收藏分享收藏An improved epsilon constraint-handling method in MOEA/D for CMOPs with large infeasible regions.png)
SOFT COMPUTING
SOFT COMPUTINGIF2.5
PREAI
分享收藏
查看更多内容