Many-objective artificial hummingbird algorithm: an effective many-objective algorithm for engineering design problems

Many-objective optimization presents unique challenges in balancing diversity and convergence of solutions. Traditional approaches struggle with this balance, leading to suboptimal solution distributions in the objective space especially at higher number of objectives. This necessitates the need for...

Full description

Saved in:
Bibliographic Details
Published in:Journal of computational design and engineering Vol. 11; no. 4; pp. 16 - 39
Main Authors: Kalita, Kanak, Jangir, Pradeep, Pandya, Sundaram B, Čep, Robert, Abualigah, Laith, Migdady, Hazem, Daoud, Mohammad Sh
Format: Journal Article
Language:English
Published: Oxford Oxford University Press 01.08.2024
한국CDE학회
Subjects:
Benchmarks
Convergence
Design engineering
Design optimization
Evolutionary algorithms
Genetic algorithms
Multiple objective analysis
Performance assessment
Sorting algorithms
기계공학
diversity preservation
many-objective optimization
multi-objective optimization
artificial hummingbird algorithm
non-dominated sorting
ISSN:2288-5048, 2288-4300, 2288-5048
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Many-objective optimization presents unique challenges in balancing diversity and convergence of solutions. Traditional approaches struggle with this balance, leading to suboptimal solution distributions in the objective space especially at higher number of objectives. This necessitates the need for innovative strategies to adeptly manage these complexities. This study introduces a Many-Objective Artificial Hummingbird Algorithm (MaOAHA), an advanced evolutionary algorithm designed to overcome the limitations of existing many-objective optimization methods. The objectives are to improve convergence rates, maintain solution diversity, and achieve a uniform distribution in the objective space. MaOAHA implements information feedback mechanism (IFM), reference point-based selection and association, non-dominated sorting, and niche preservation. The IFM utilizes historical data from previous generations to inform the update process, thereby improving the algorithm’s the exploration and exploitation capabilities. Reference point-based selection, along with non-dominated sorting, ensures solutions are both close to the Pareto front and evenly spread in the objective space. Niche preservation and density estimation strategies are employed to maintain diversity and prevent overcrowding. The comprehensive experimental analysis benchmarks MaOAHA against four leading algorithms viz. Many-Objective Gradient-Based Optimizer, Many-Objective Particle Swarm Optimizer, Reference Vector Guided Evolutionary Algorithm, and Nondominated Sorting Genetic Algorithm III. The DTLZ1–DTLZ7 benchmark sets with four, six, and eight objectives and five real-world problems (RWMaOP1–RWMaOP5) are considered for performance assessment of the selected algorithms. The results demonstrate that internal parameter-free MaOAHA significantly outperforms its counterparts, achieving better generational distance by up to 52.38%, inverse generational distance by up to 38.09%, spacing by up to 56%, spread by up to 71.42%, hypervolume by up to 44%, and runtime by up to 52%. These metrics affirm the MaOAHA’s capability to enhance the decision-making processes through its adept balance of convergence, diversity, and uniformity. Graphical Abstract Graphical Abstract
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2288-5048
2288-4300
2288-5048
DOI:10.1093/jcde/qwae055