.png){kind=icon}
.png){kind=icon}
Return
Objective transformation-based and niche-based many-objective evolutionary algorithm with a two-step coordination mechanism
.png){kind=icon}
PRE
AI
DOI：10.1016/j.engappai.2024.109850.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Evolutionary algorithms have emerged as powerful tools for optimization. However, striking a balance between convergence and diversity in many-objective optimization remains a significant challenge. To address this gap, we propose TSEA-OTN, an objective transformation-based and niche-based many-objective evolutionary algorithm with a two-step coordination mechanism. Uniquely, TSEA-OTN operates without relying on relaxed Pareto dominance, reference vectors, or additional indicators. Instead, it utilizes prior knowledge about the curvature of the PF (Pareto optimal front) to transform the objectives of the population and establish niches. Additionally, a niche-assisted density estimation method is designed to measure the distribution of individual. The environmental selection process incorporates a two-step mechanism: in the former step, the niche-assisted density evaluation method identifies crowded individuals to prioritize diversity; in the latter step, the Euclidean distance among transformed individuals and convergence evaluation criteria are used to eliminate individuals within the same niche for promoting convergence. Finally, TSEA-OTN is evaluated against six state-of-the-art algorithms on DTLZ (Deb-Thiele-Laumanns-Zitzler), MaF (Many-objective function), WGF (Walking Fish Group) benchmark suites, as well as an engineering case study. Experimental results demonstrate the competitive performance of TSEA-OTN in solving many-objective optimization problems. This research not only advances the field of evolutionary computation but also provides novel solutions for real-world optimization.
Keywords:
Evolutionary algorithms
Many-objective optimization
Objective transformation
Niche
Journal
IF:
8
Papers:
5.4K
Citations:
3.5W