Machine learning for predicting resistance spot weld quality in automotive manufacturing

Resistance Spot Welding (RSW) stands as the primary joining process in the automotive industry, renowned for its suitability for automation and integration into high-production assembly lines. Despite its advantages, accurately evaluating RSW remains challenging, resulting in additional costs and pr...

Full description

Saved in:
Bibliographic Details
Main Authors: Nuttapong Chuenmee, Nattachai Phothi, Kontorn Chamniprasart, Sorada Khaengkarn, Jiraphon Srisertpol
Format: Article
Language:English
Published: Elsevier 2025-03-01
Series:Results in Engineering
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2590123024018139
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846107642136625152
author Nuttapong Chuenmee
Nattachai Phothi
Kontorn Chamniprasart
Sorada Khaengkarn
Jiraphon Srisertpol
author_facet Nuttapong Chuenmee
Nattachai Phothi
Kontorn Chamniprasart
Sorada Khaengkarn
Jiraphon Srisertpol
author_sort Nuttapong Chuenmee
collection DOAJ
description Resistance Spot Welding (RSW) stands as the primary joining process in the automotive industry, renowned for its suitability for automation and integration into high-production assembly lines. Despite its advantages, accurately evaluating RSW remains challenging, resulting in additional costs and production steps. Current inspection methods, reliant on random checks after cars leave the Body-in-White (BIW), often lead to significant time losses, emphasizing the necessity for enhanced quality assessment. This study aims to transition from random checks to 100 percent inspection using data analysis and machine learning techniques. By predicting weld quality levels prior to car body completion, this approach aims to improve quality control. Five distinct algorithms—Artificial Neural Network (ANN), Convolution Neural Network (CNN), Long Short-Term Memory (LSTM), Random Forest Classifier (RFC), and Extreme Gradient Boosting (XGBoost)—were assessed. The research highlights that the proposed methodology, particularly leveraging XGBoost, achieves a notable prediction accuracy of 97.1% when applied to unseen data.
format Article
id doaj-art-7a8f5ed1727a4ea3a3aa6daf1c4f725d
institution Kabale University
issn 2590-1230
language English
publishDate 2025-03-01
publisher Elsevier
record_format Article
series Results in Engineering
spelling doaj-art-7a8f5ed1727a4ea3a3aa6daf1c4f725d2024-12-26T08:57:28ZengElsevierResults in Engineering2590-12302025-03-0125103570Machine learning for predicting resistance spot weld quality in automotive manufacturingNuttapong Chuenmee0Nattachai Phothi1Kontorn Chamniprasart2Sorada Khaengkarn3Jiraphon Srisertpol4Mechatronics Engineering Program, School of Mechanical Engineering, Suranaree University of Technology, Nakhon Ratchasima, ThailandDepartment of Production Engineering Technology, Faculty of Industrial Technology, Loei Rajabhat University, Loei, ThailandMechatronics Engineering Program, School of Mechanical Engineering, Suranaree University of Technology, Nakhon Ratchasima, ThailandMechatronics Engineering Program, School of Mechanical Engineering, Suranaree University of Technology, Nakhon Ratchasima, ThailandMechatronics Engineering Program, School of Mechanical Engineering, Suranaree University of Technology, Nakhon Ratchasima, Thailand; Corresponding author.Resistance Spot Welding (RSW) stands as the primary joining process in the automotive industry, renowned for its suitability for automation and integration into high-production assembly lines. Despite its advantages, accurately evaluating RSW remains challenging, resulting in additional costs and production steps. Current inspection methods, reliant on random checks after cars leave the Body-in-White (BIW), often lead to significant time losses, emphasizing the necessity for enhanced quality assessment. This study aims to transition from random checks to 100 percent inspection using data analysis and machine learning techniques. By predicting weld quality levels prior to car body completion, this approach aims to improve quality control. Five distinct algorithms—Artificial Neural Network (ANN), Convolution Neural Network (CNN), Long Short-Term Memory (LSTM), Random Forest Classifier (RFC), and Extreme Gradient Boosting (XGBoost)—were assessed. The research highlights that the proposed methodology, particularly leveraging XGBoost, achieves a notable prediction accuracy of 97.1% when applied to unseen data.http://www.sciencedirect.com/science/article/pii/S2590123024018139Resistance spot welding (RSW)Weld inspectionWeld quality classificationData analysisMachine learning
spellingShingle Nuttapong Chuenmee
Nattachai Phothi
Kontorn Chamniprasart
Sorada Khaengkarn
Jiraphon Srisertpol
Machine learning for predicting resistance spot weld quality in automotive manufacturing
Results in Engineering
Resistance spot welding (RSW)
Weld inspection
Weld quality classification
Data analysis
Machine learning
title Machine learning for predicting resistance spot weld quality in automotive manufacturing
title_full Machine learning for predicting resistance spot weld quality in automotive manufacturing
title_fullStr Machine learning for predicting resistance spot weld quality in automotive manufacturing
title_full_unstemmed Machine learning for predicting resistance spot weld quality in automotive manufacturing
title_short Machine learning for predicting resistance spot weld quality in automotive manufacturing
title_sort machine learning for predicting resistance spot weld quality in automotive manufacturing
topic Resistance spot welding (RSW)
Weld inspection
Weld quality classification
Data analysis
Machine learning
url http://www.sciencedirect.com/science/article/pii/S2590123024018139
work_keys_str_mv AT nuttapongchuenmee machinelearningforpredictingresistancespotweldqualityinautomotivemanufacturing
AT nattachaiphothi machinelearningforpredictingresistancespotweldqualityinautomotivemanufacturing
AT kontornchamniprasart machinelearningforpredictingresistancespotweldqualityinautomotivemanufacturing
AT soradakhaengkarn machinelearningforpredictingresistancespotweldqualityinautomotivemanufacturing
AT jiraphonsrisertpol machinelearningforpredictingresistancespotweldqualityinautomotivemanufacturing