Comparison of Two Machine Learning Models for Predicting Volumetric Errors From On-The-Fly R-Test Type Device Data and Virtual End Point Constraints

On-the-fly virtual end-point constraints consists in moving all five axes of the machine tool while nominally maintaining the coincidence of a sensing head centre point with a master ball centre attached to the workpiece table. The sensing head detects the deviations from the nominal coincidence as...

Full description

Saved in:
Bibliographic Details
Main Authors: Min Zeng, J. R. R. Mayer, Miao Feng, Elie Bitar-Nehme, Xuan Truong Duong
Format: Article
Language:English
Published: Publishing House of Wrocław Board of Scientific Technical Societies Federation NOT 2025-05-01
Series:Journal of Machine Engineering
Subjects:
Online Access:http://jmacheng.not.pl/Comparison-of-Two-Machine-Learning-Models-for-Predicting-Volumetric-Errors-From-On,203805,0,2.html
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849336118485450752
author Min Zeng
J. R. R. Mayer
Miao Feng
Elie Bitar-Nehme
Xuan Truong Duong
author_facet Min Zeng
J. R. R. Mayer
Miao Feng
Elie Bitar-Nehme
Xuan Truong Duong
author_sort Min Zeng
collection DOAJ
description On-the-fly virtual end-point constraints consists in moving all five axes of the machine tool while nominally maintaining the coincidence of a sensing head centre point with a master ball centre attached to the workpiece table. The sensing head detects the deviations from the nominal coincidence as a 3D volumetric error vector. More than one ball can be so measured and a fixed length ball bar is also measured for detecting isotropic scaling effects. Initial processing of data using the SAMBA (scale and master ball artefact) method eliminates setup errors and provides estimates of inter- and intra-axis errors as well as volumetric errors vectors. Two ML models are trained and compared, Neural Network (NN) and eXtreme Gradient Boosting (XGBoost), to find the most suitable model and the required amount of training data to predict volumetric errors of a five-axis machine tool with wCBXfZY(S)t topology based on axis commands. The results show that NN marginally outperforms XGBoost and a kinematic model with ratios of prediction error over volumetric error norms of 0.12, 0.13 and 0.14, respectively.
format Article
id doaj-art-427ec99a464c40afa96a8fce9032e952
institution Kabale University
issn 1895-7595
2391-8071
language English
publishDate 2025-05-01
publisher Publishing House of Wrocław Board of Scientific Technical Societies Federation NOT
record_format Article
series Journal of Machine Engineering
spelling doaj-art-427ec99a464c40afa96a8fce9032e9522025-08-20T03:45:04ZengPublishing House of Wrocław Board of Scientific Technical Societies Federation NOTJournal of Machine Engineering1895-75952391-80712025-05-01252132710.36897/jme/203805203805Comparison of Two Machine Learning Models for Predicting Volumetric Errors From On-The-Fly R-Test Type Device Data and Virtual End Point ConstraintsMin Zeng0J. R. R. Mayer1Miao Feng2Elie Bitar-Nehme3Xuan Truong Duong4Department of Mechanical Engineering, Polytechnique Montréal, CanadaDepartment of Mechanical Engineering, Polytechnique Montréal, CanadaDepartment of Computer Science and Operations Research, Université de Montréal, CanadaDepartment of Mechanical Engineering, Polytechnique Montréal, CanadaDepartment of Mechanical Engineering, Dawson College, CanadaOn-the-fly virtual end-point constraints consists in moving all five axes of the machine tool while nominally maintaining the coincidence of a sensing head centre point with a master ball centre attached to the workpiece table. The sensing head detects the deviations from the nominal coincidence as a 3D volumetric error vector. More than one ball can be so measured and a fixed length ball bar is also measured for detecting isotropic scaling effects. Initial processing of data using the SAMBA (scale and master ball artefact) method eliminates setup errors and provides estimates of inter- and intra-axis errors as well as volumetric errors vectors. Two ML models are trained and compared, Neural Network (NN) and eXtreme Gradient Boosting (XGBoost), to find the most suitable model and the required amount of training data to predict volumetric errors of a five-axis machine tool with wCBXfZY(S)t topology based on axis commands. The results show that NN marginally outperforms XGBoost and a kinematic model with ratios of prediction error over volumetric error norms of 0.12, 0.13 and 0.14, respectively.http://jmacheng.not.pl/Comparison-of-Two-Machine-Learning-Models-for-Predicting-Volumetric-Errors-From-On,203805,0,2.htmlmachine learningfive-axis machine toolvolumetric errorsr-test
spellingShingle Min Zeng
J. R. R. Mayer
Miao Feng
Elie Bitar-Nehme
Xuan Truong Duong
Comparison of Two Machine Learning Models for Predicting Volumetric Errors From On-The-Fly R-Test Type Device Data and Virtual End Point Constraints
Journal of Machine Engineering
machine learning
five-axis machine tool
volumetric errors
r-test
title Comparison of Two Machine Learning Models for Predicting Volumetric Errors From On-The-Fly R-Test Type Device Data and Virtual End Point Constraints
title_full Comparison of Two Machine Learning Models for Predicting Volumetric Errors From On-The-Fly R-Test Type Device Data and Virtual End Point Constraints
title_fullStr Comparison of Two Machine Learning Models for Predicting Volumetric Errors From On-The-Fly R-Test Type Device Data and Virtual End Point Constraints
title_full_unstemmed Comparison of Two Machine Learning Models for Predicting Volumetric Errors From On-The-Fly R-Test Type Device Data and Virtual End Point Constraints
title_short Comparison of Two Machine Learning Models for Predicting Volumetric Errors From On-The-Fly R-Test Type Device Data and Virtual End Point Constraints
title_sort comparison of two machine learning models for predicting volumetric errors from on the fly r test type device data and virtual end point constraints
topic machine learning
five-axis machine tool
volumetric errors
r-test
url http://jmacheng.not.pl/Comparison-of-Two-Machine-Learning-Models-for-Predicting-Volumetric-Errors-From-On,203805,0,2.html
work_keys_str_mv AT minzeng comparisonoftwomachinelearningmodelsforpredictingvolumetricerrorsfromontheflyrtesttypedevicedataandvirtualendpointconstraints
AT jrrmayer comparisonoftwomachinelearningmodelsforpredictingvolumetricerrorsfromontheflyrtesttypedevicedataandvirtualendpointconstraints
AT miaofeng comparisonoftwomachinelearningmodelsforpredictingvolumetricerrorsfromontheflyrtesttypedevicedataandvirtualendpointconstraints
AT eliebitarnehme comparisonoftwomachinelearningmodelsforpredictingvolumetricerrorsfromontheflyrtesttypedevicedataandvirtualendpointconstraints
AT xuantruongduong comparisonoftwomachinelearningmodelsforpredictingvolumetricerrorsfromontheflyrtesttypedevicedataandvirtualendpointconstraints