Predicting thrust force during drilling of composite laminates with step drills through the Gaussian process regression

PurposeHere, the authors use step angles, stage ratios, feed rates and spindle speeds as predictors to develop a Gaussian process regression for predicting thrust force during composite laminates drilling with step drills.Design/methodology/approachUse of machine learning methods could benefit machi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Multidiscipline modeling in materials and structures Jg. 18; H. 5; S. 845 - 855
Hauptverfasser: Zhang, Yun, Xu, Xiaojie
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Bingley Emerald Publishing Limited 12.10.2022
Emerald Group Publishing Limited
Schlagworte:
Algorithms
Carbon fibers
Composite materials
Cost effectiveness
Design of experiments
Drilling
Drilling machines (tools)
Drills
Feed rate
Fractals
Gaussian process
Industrial applications
Laminates
Machine learning
Machining
Neural networks
Optimization
Polymers
Regression
Taguchi methods
Thrust
Variables
Drilling
Gaussian process regression
Composite material
Thrust force
Machine learning
ISSN:1573-6105, 1573-6113
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:PurposeHere, the authors use step angles, stage ratios, feed rates and spindle speeds as predictors to develop a Gaussian process regression for predicting thrust force during composite laminates drilling with step drills.Design/methodology/approachUse of machine learning methods could benefit machining process optimizations. Accurate, stable and robust performance is one of major criteria in choosing among different models. For industrial applications, it is also important to consider model applicability, ease of implementations and cost effectiveness.FindingsThis model turns out to be simple, accurate and stable, which helps fast estimates of thrust force. Through combining the Taguchi method's optimization results and the Gaussian process regression, more data could be expected to be extracted through fewer experiments.Originality/valueThrough combining the Taguchi method's optimization results and the Gaussian process regression, more data could be expected to be extracted through fewer experiments.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1573-6105
1573-6113
DOI:10.1108/MMMS-07-2022-0123