Cutting Force Prediction of Ti6Al4V using a Machine Learning Model of SPH Orthogonal Cutting Process Simulations

The prediction of machining processes is a challenging task and usually requires a large experimental basis. These experiments are time-consuming and require manufacturing and testing of different tool geometries at various process conditions to find optimum machining settings. In this paper, a mach...

Full description

Saved in:
Bibliographic Details
Main Authors: Hagen Klippel, Eduardo Gonzalez Sanchez, Margolis Isabel, Matthias Röthlin, Mohamadreza Afrasiabi, Kuffa Michal, Konrad Wegener
Format: Article
Language:English
Published: Publishing House of Wrocław Board of Scientific Technical Societies Federation NOT 2022-03-01
Series:Journal of Machine Engineering
Subjects:
Online Access:http://jmacheng.not.pl/Cutting-Force-Prediction-of-Ti6Al4V-using-a-Machine-Learning-Model-of-SPH-Orthogonal,147201,0,2.html
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849773677509345280
author Hagen Klippel
Eduardo Gonzalez Sanchez
Margolis Isabel
Matthias Röthlin
Mohamadreza Afrasiabi
Kuffa Michal
Konrad Wegener
author_facet Hagen Klippel
Eduardo Gonzalez Sanchez
Margolis Isabel
Matthias Röthlin
Mohamadreza Afrasiabi
Kuffa Michal
Konrad Wegener
author_sort Hagen Klippel
collection DOAJ
description The prediction of machining processes is a challenging task and usually requires a large experimental basis. These experiments are time-consuming and require manufacturing and testing of different tool geometries at various process conditions to find optimum machining settings. In this paper, a machine learning model of the orthogonal cutting process of Ti6Al4V is proposed to predict the cutting and feed forces for a wide range of process conditions with regards to rake angle, clearance angle, cutting edge radius, feed and cutting speed. The model uses training data generated by virtual experiments, which are conducted using physical based simulations of the orthogonal cutting process with the smoothed particle hydrodynamics (SPH). The ML training set is composed of input parameters, and output process forces from 2500 instances of GPU accelerated SPH simulations. The resulting model provides fast process force predictions and can consider the cutter geometry in comparison to classical analytical approaches.
format Article
id doaj-art-69f97244e0db42ec9ea24409c93c6ca5
institution DOAJ
issn 1895-7595
2391-8071
language English
publishDate 2022-03-01
publisher Publishing House of Wrocław Board of Scientific Technical Societies Federation NOT
record_format Article
series Journal of Machine Engineering
spelling doaj-art-69f97244e0db42ec9ea24409c93c6ca52025-08-20T03:01:58ZengPublishing House of Wrocław Board of Scientific Technical Societies Federation NOTJournal of Machine Engineering1895-75952391-80712022-03-0122111112310.36897/jme/147201147201Cutting Force Prediction of Ti6Al4V using a Machine Learning Model of SPH Orthogonal Cutting Process SimulationsHagen Klippel0Eduardo Gonzalez Sanchez1Margolis Isabel2Matthias Röthlin3Mohamadreza Afrasiabi4Kuffa Michal5Konrad Wegener6IWF, ETH Zürich, SwitzerlandIWF, ETH Zürich, SwitzerlandIWF/inspire, ETH Zürich, SwitzerlandFederal Office of Meteorology & Climatology, MeteoSwiss, Switzerland, SwitzerlandIWF/inspire, ETH Zürich, SwitzerlandIWF, ETH Zürich, SwitzerlandIWF, ETH Zürich, SwitzerlandThe prediction of machining processes is a challenging task and usually requires a large experimental basis. These experiments are time-consuming and require manufacturing and testing of different tool geometries at various process conditions to find optimum machining settings. In this paper, a machine learning model of the orthogonal cutting process of Ti6Al4V is proposed to predict the cutting and feed forces for a wide range of process conditions with regards to rake angle, clearance angle, cutting edge radius, feed and cutting speed. The model uses training data generated by virtual experiments, which are conducted using physical based simulations of the orthogonal cutting process with the smoothed particle hydrodynamics (SPH). The ML training set is composed of input parameters, and output process forces from 2500 instances of GPU accelerated SPH simulations. The resulting model provides fast process force predictions and can consider the cutter geometry in comparison to classical analytical approaches.http://jmacheng.not.pl/Cutting-Force-Prediction-of-Ti6Al4V-using-a-Machine-Learning-Model-of-SPH-Orthogonal,147201,0,2.htmlti6al4vsphmachiningmachine learning
spellingShingle Hagen Klippel
Eduardo Gonzalez Sanchez
Margolis Isabel
Matthias Röthlin
Mohamadreza Afrasiabi
Kuffa Michal
Konrad Wegener
Cutting Force Prediction of Ti6Al4V using a Machine Learning Model of SPH Orthogonal Cutting Process Simulations
Journal of Machine Engineering
ti6al4v
sph
machining
machine learning
title Cutting Force Prediction of Ti6Al4V using a Machine Learning Model of SPH Orthogonal Cutting Process Simulations
title_full Cutting Force Prediction of Ti6Al4V using a Machine Learning Model of SPH Orthogonal Cutting Process Simulations
title_fullStr Cutting Force Prediction of Ti6Al4V using a Machine Learning Model of SPH Orthogonal Cutting Process Simulations
title_full_unstemmed Cutting Force Prediction of Ti6Al4V using a Machine Learning Model of SPH Orthogonal Cutting Process Simulations
title_short Cutting Force Prediction of Ti6Al4V using a Machine Learning Model of SPH Orthogonal Cutting Process Simulations
title_sort cutting force prediction of ti6al4v using a machine learning model of sph orthogonal cutting process simulations
topic ti6al4v
sph
machining
machine learning
url http://jmacheng.not.pl/Cutting-Force-Prediction-of-Ti6Al4V-using-a-Machine-Learning-Model-of-SPH-Orthogonal,147201,0,2.html
work_keys_str_mv AT hagenklippel cuttingforcepredictionofti6al4vusingamachinelearningmodelofsphorthogonalcuttingprocesssimulations
AT eduardogonzalezsanchez cuttingforcepredictionofti6al4vusingamachinelearningmodelofsphorthogonalcuttingprocesssimulations
AT margolisisabel cuttingforcepredictionofti6al4vusingamachinelearningmodelofsphorthogonalcuttingprocesssimulations
AT matthiasrothlin cuttingforcepredictionofti6al4vusingamachinelearningmodelofsphorthogonalcuttingprocesssimulations
AT mohamadrezaafrasiabi cuttingforcepredictionofti6al4vusingamachinelearningmodelofsphorthogonalcuttingprocesssimulations
AT kuffamichal cuttingforcepredictionofti6al4vusingamachinelearningmodelofsphorthogonalcuttingprocesssimulations
AT konradwegener cuttingforcepredictionofti6al4vusingamachinelearningmodelofsphorthogonalcuttingprocesssimulations