Mühendislik Problemlerinin Optimizasyonu için Evrimsel Algoritmalar
No Thumbnail Available
Date
2025
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Open Access Color
OpenAIRE Downloads
OpenAIRE Views
Abstract
Üç boyutlu yumuşak büyüyen robotik manipülatörlerin tasarımını gerçekleştirmeyi amaçlayan çok amaçlı sürekli evrimsel bir çerçeve öneriyoruz. Ulaşılabilirlik, malzeme kullanımı, eğrilik düzgünlüğü ve çarpışmasız alanı tek bir optimizasyon problemine dahil ederek, ağırlık ayarlamasını ve karmaşık Pareto ön yüzü hesaplamalarını ortadan kaldırmak için Sıralama Bölme (Rank Partitioning) ve hayatta kalma stratejilerinden faydalanıyoruz. Dört algoritmayı, Genetik Algoritma (GA), Parçacık Sürüsü Optimizasyonu (PSO), Diferansiyel Evrim (DE) ve Büyük Patlama–Büyük Çöküş (BB–BC), aynı koşullar altında, farklı hedefler ve engeller ile karşılaştırdık. Sonuçlar, bu mühendislik problemi için en iyi algoritmaların sırasıyla GA ve PSO olduğunu, ardından DE'nin geldiğini göstermektedir; ayrıca BB–BC'nin ortalama olarak PSO ve DE'ye kıyasla daha tutarlı olduğunu iddia ediyoruz. Yaklaşımımız, sürekli robot tasarımı için ölçeklenebilir bir çözümdür ve karmaşık, yapısal olmayan alanlar için en uygun algoritmanın seçilmesine yardımcı olur.
The 3D design of soft growing robotic manipulators is a demanding task due to theirbuilt-in compliance and the need to optimize several, typically conflicting, objec-tives. This thesis presents a novel multi-objective continuous evolutionary methodfor 3D design of such manipulators. Our approach integrates key factors such asreachability, material efficiency, curvature smoothness, and collision avoidance into asingle optimization problem. By leveraging Rank Partitioning and effective survivalmethods, our approach avoids manual weight tuning and expensive Pareto-front cal-culations. We performed an extensive comparative study of four evolutionary algo-rithms, Genetic Algorithm (GA), Particle Swarm Optimization (PSO), DifferentialEvolution (DE), and Big Bang-Big Crunch (BB-BC), under the same conditionson different targets and obstacles. Results show that GA and PSO always providesuperior performance for this design problem, while BB-BC is illustrated as beingvery consistent relative to PSO and DE. Scalable solution significantly advancescontinuum robot design since it enables the selection of the optimal algorithm forthis engineering problem.
The 3D design of soft growing robotic manipulators is a demanding task due to theirbuilt-in compliance and the need to optimize several, typically conflicting, objec-tives. This thesis presents a novel multi-objective continuous evolutionary methodfor 3D design of such manipulators. Our approach integrates key factors such asreachability, material efficiency, curvature smoothness, and collision avoidance into asingle optimization problem. By leveraging Rank Partitioning and effective survivalmethods, our approach avoids manual weight tuning and expensive Pareto-front cal-culations. We performed an extensive comparative study of four evolutionary algo-rithms, Genetic Algorithm (GA), Particle Swarm Optimization (PSO), DifferentialEvolution (DE), and Big Bang-Big Crunch (BB-BC), under the same conditionson different targets and obstacles. Results show that GA and PSO always providesuperior performance for this design problem, while BB-BC is illustrated as beingvery consistent relative to PSO and DE. Scalable solution significantly advancescontinuum robot design since it enables the selection of the optimal algorithm forthis engineering problem.
Description
Keywords
Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrol, Computer Engineering and Computer Science and Control
Turkish CoHE Thesis Center URL
Fields of Science
Citation
WoS Q
Scopus Q
Source
Volume
Issue
Start Page
End Page
121
Collections
Page Views
1
checked on Nov 27, 2025
Google Scholar™
Sustainable Development Goals
3
GOOD HEALTH AND WELL-BEING

6
CLEAN WATER AND SANITATION

7
AFFORDABLE AND CLEAN ENERGY

8
DECENT WORK AND ECONOMIC GROWTH

9
INDUSTRY, INNOVATION AND INFRASTRUCTURE

11
SUSTAINABLE CITIES AND COMMUNITIES

12
RESPONSIBLE CONSUMPTION AND PRODUCTION

13
CLIMATE ACTION
