Optimization of Process Parameters for Surface Roughness and Milling Power of AL7075 CNC Milling Based on a Hybrid Multi-Objective Particle Swarm Optimization Integrating Whale Optimization Algorithm

In the process of computer numerical control (CNC) corner milling, surface roughness and milling power are two important objectives. Surface roughness can reflect the machining quality to a certain extent, while the milling power can characterize the machining energy consumption. If the process para...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Integrating materials and manufacturing innovation Jg. 14; H. 3; S. 401 - 424
Hauptverfasser: Yang, Yang, Wei, Xinbei
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Cham Springer International Publishing 01.09.2025
Springer Nature B.V
Schlagworte:
Accuracy
Algorithms
Avalanche diodes
Characterization and Evaluation of Materials
Chemistry and Materials Science
Design optimization
Efficiency
Energy consumption
Genetic algorithms
Manufacturing
Materials Science
Metallic Materials
Milling (machining)
Multiple objective analysis
Nanotechnology
Neural networks
Numerical controls
Objectives
Optimization algorithms
Particle swarm optimization
Process parameters
Product quality
Structural Materials
Support vector machines
Surface roughness
Surfaces and Interfaces
Technical Article
Thin Films
Transistor logic
Hybrid algorithms
Machining dynamics
Parameters optimization
Energy efficient milling
Surface roughness
CNC milling
ISSN:2193-9764, 2193-9772
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In the process of computer numerical control (CNC) corner milling, surface roughness and milling power are two important objectives. Surface roughness can reflect the machining quality to a certain extent, while the milling power can characterize the machining energy consumption. If the process parameters are improper, it will lead to unnecessary energy consumption and even the decline of processing quality. Optimizing the process parameters can reduce energy consumption while maintaining process quality. In this paper, a hybrid multi-objective particle swarm optimization integrating whale optimization algorithm (MOPSOWOA) is proposed. The unique update iteration mode of whale optimization algorithm (WOA) is introduced into that of particle swarm optimization (PSO) algorithm through crossover and replacement, improving the global search ability and local exploration ability of PSO. The proposed MOPSOWOA is compared with four other multi-objective optimization algorithms on 19 benchmark functions of Zitzler–Deb–Thiele test functions (ZDT), diode-transistor logic with Zener diode (DTLZ) and Walking Fish Group (WFG) series. Taking inverse generation distance (IGD) and hypervolume (HV) as evaluation indexes, MOPSOWOA shows excellent performance in the results of mean value, variance and Wilcoxon rank-sum test. Finally, the models of surface roughness and milling power of AL7075 corner milling are constructed by support vector regression (SVR). MOPSOWOA is adopted to optimize the process parameters by solving the above models, and a satisfactory combination of machining parameters is obtained compared with MOPSO and NSGA-II.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2193-9764
2193-9772
DOI:10.1007/s40192-025-00412-7