Prediction of laser welding qualities of Al alloys using regression and machine learning techniques

This work compared different machine learning models such as linear regression, polynomial regression and XG-Boost for the prediction of laser welding qualities in aluminum alloys. The key weld quality parameters are ultimate load, weld width and penetration depth. Each model was trained and validat...

Full description

Saved in:
Bibliographic Details
Main Authors: Hemant Kumar, Soumyabrata Chakravarty, Nitesh Kuamr, Nikhil Kumar
Format: Article
Language:English
Published: IOP Publishing 2025-01-01
Series:Materials Research Express
Subjects:
Online Access:https://doi.org/10.1088/2053-1591/addd68
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850098899655589888
author Hemant Kumar
Soumyabrata Chakravarty
Nitesh Kuamr
Nikhil Kumar
author_facet Hemant Kumar
Soumyabrata Chakravarty
Nitesh Kuamr
Nikhil Kumar
author_sort Hemant Kumar
collection DOAJ
description This work compared different machine learning models such as linear regression, polynomial regression and XG-Boost for the prediction of laser welding qualities in aluminum alloys. The key weld quality parameters are ultimate load, weld width and penetration depth. Each model was trained and validated based on data experimentally collected by varying laser power, scanning speed and offset distance to compare them. Quantitative results are shown to prove that XG-Boost produces a better predictive accuracy, as it gives a root mean square error (RMSE) of 0.05 for ultimate load, 0.03 for penetration depth, and 0.02 for weld width. On the other hand, its linear regression counterpart has higher values of 0.08, 0.06, and 0.05, while polynomial regression-clearly outperforming its linear variant-averaged about 0.04 in these metrics. While this is so, high R-squared values, predicted by the XG-Boost model across ultimate loads, are indicative of its better competency in the capturing of complicated patterns, especially with regard to data outliers. These findings confirm the capability of XG-Boost to perform precise parameter optimization in laser welding by significantly reducing experimental trial needs and helping manufacturing efficiency with reliable data-driven predictions.
format Article
id doaj-art-5d2ae2ad568f41e68dfed6def4ba8bfc
institution DOAJ
issn 2053-1591
language English
publishDate 2025-01-01
publisher IOP Publishing
record_format Article
series Materials Research Express
spelling doaj-art-5d2ae2ad568f41e68dfed6def4ba8bfc2025-08-20T02:40:36ZengIOP PublishingMaterials Research Express2053-15912025-01-0112606650110.1088/2053-1591/addd68Prediction of laser welding qualities of Al alloys using regression and machine learning techniquesHemant Kumar0https://orcid.org/0009-0007-2097-8072Soumyabrata Chakravarty1https://orcid.org/0000-0002-3579-9161Nitesh Kuamr2https://orcid.org/0009-0006-7123-2409Nikhil Kumar3https://orcid.org/0009-0007-3873-6477Computer Science & Engineering Department, Kalinga Institute of Technology, Bhubaneswar, 751024, Odisha, IndiaMechanical Engineering Department, Jadavpur University , Kolkata, 700032, West Bengal, India; Mechanical Engineering Department, Brainware University , Kolkata, 700125, West Bengal, IndiaMechanical Engineering Department, Jadavpur University , Kolkata, 700032, West Bengal, India; Mechanical Engineering Department, Brainware University , Kolkata, 700125, West Bengal, IndiaWarwick Manufacturing Group, The University of Warwick , Coventry CV 4 7AL, United KingdomThis work compared different machine learning models such as linear regression, polynomial regression and XG-Boost for the prediction of laser welding qualities in aluminum alloys. The key weld quality parameters are ultimate load, weld width and penetration depth. Each model was trained and validated based on data experimentally collected by varying laser power, scanning speed and offset distance to compare them. Quantitative results are shown to prove that XG-Boost produces a better predictive accuracy, as it gives a root mean square error (RMSE) of 0.05 for ultimate load, 0.03 for penetration depth, and 0.02 for weld width. On the other hand, its linear regression counterpart has higher values of 0.08, 0.06, and 0.05, while polynomial regression-clearly outperforming its linear variant-averaged about 0.04 in these metrics. While this is so, high R-squared values, predicted by the XG-Boost model across ultimate loads, are indicative of its better competency in the capturing of complicated patterns, especially with regard to data outliers. These findings confirm the capability of XG-Boost to perform precise parameter optimization in laser welding by significantly reducing experimental trial needs and helping manufacturing efficiency with reliable data-driven predictions.https://doi.org/10.1088/2053-1591/addd68machine learningweld qualityXG boostregressionaluminium alloy
spellingShingle Hemant Kumar
Soumyabrata Chakravarty
Nitesh Kuamr
Nikhil Kumar
Prediction of laser welding qualities of Al alloys using regression and machine learning techniques
Materials Research Express
machine learning
weld quality
XG boost
regression
aluminium alloy
title Prediction of laser welding qualities of Al alloys using regression and machine learning techniques
title_full Prediction of laser welding qualities of Al alloys using regression and machine learning techniques
title_fullStr Prediction of laser welding qualities of Al alloys using regression and machine learning techniques
title_full_unstemmed Prediction of laser welding qualities of Al alloys using regression and machine learning techniques
title_short Prediction of laser welding qualities of Al alloys using regression and machine learning techniques
title_sort prediction of laser welding qualities of al alloys using regression and machine learning techniques
topic machine learning
weld quality
XG boost
regression
aluminium alloy
url https://doi.org/10.1088/2053-1591/addd68
work_keys_str_mv AT hemantkumar predictionoflaserweldingqualitiesofalalloysusingregressionandmachinelearningtechniques
AT soumyabratachakravarty predictionoflaserweldingqualitiesofalalloysusingregressionandmachinelearningtechniques
AT niteshkuamr predictionoflaserweldingqualitiesofalalloysusingregressionandmachinelearningtechniques
AT nikhilkumar predictionoflaserweldingqualitiesofalalloysusingregressionandmachinelearningtechniques