Resistance Welding Quality Through Artificial Intelligence Techniques

Quality assessment of the resistance spot welding process (RSW) is vital during manufacturing. Evaluating the quality without altering the joint material’s physical and mechanical properties has gained interest. This study uses a trained computer vision model to propose a cheap, non-destructive qual...

Full description

Saved in:
Bibliographic Details
Main Authors: Luis Alonso Domínguez-Molina, Edgar Rivas-Araiza, Juan Carlos Jauregui-Correa, Jose Luis Gonzalez-Cordoba, Jesús Carlos Pedraza-Ortega, Andras Takacs
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/6/1744
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850088232299003904
author Luis Alonso Domínguez-Molina
Edgar Rivas-Araiza
Juan Carlos Jauregui-Correa
Jose Luis Gonzalez-Cordoba
Jesús Carlos Pedraza-Ortega
Andras Takacs
author_facet Luis Alonso Domínguez-Molina
Edgar Rivas-Araiza
Juan Carlos Jauregui-Correa
Jose Luis Gonzalez-Cordoba
Jesús Carlos Pedraza-Ortega
Andras Takacs
author_sort Luis Alonso Domínguez-Molina
collection DOAJ
description Quality assessment of the resistance spot welding process (RSW) is vital during manufacturing. Evaluating the quality without altering the joint material’s physical and mechanical properties has gained interest. This study uses a trained computer vision model to propose a cheap, non-destructive quality-evaluation methodology. The methodology connects the welding input and during-process parameters with the output visual quality information. A manual resistance spot welding machine was used to monitor and record the process input and output parameters to generate the dataset for training. The welding current, welding time, and electrode pressure data were correlated with the welding spot nugget’s quality, mechanical characteristics, and thermal and visible images. Six machine learning models were trained on visible and thermographic images to classify the weld’s quality and connect the quality characteristics (pull force and welding diameter) and the manufacturing process parameters with the visible and thermographic images of the weld. Finally, a cross-validation method validated the robustness of these models. The results indicate that the welding time and the angle between electrodes are highly influential parameters on the mechanical strength of the joint. Additionally, models using visible images of the welding spot exhibited superior performance compared to thermal images.
format Article
id doaj-art-28e04937acf54aa0b45e1d992ef6eda5
institution DOAJ
issn 1424-8220
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-28e04937acf54aa0b45e1d992ef6eda52025-08-20T02:43:03ZengMDPI AGSensors1424-82202025-03-01256174410.3390/s25061744Resistance Welding Quality Through Artificial Intelligence TechniquesLuis Alonso Domínguez-Molina0Edgar Rivas-Araiza1Juan Carlos Jauregui-Correa2Jose Luis Gonzalez-Cordoba3Jesús Carlos Pedraza-Ortega4Andras Takacs5Facultad de Ingeniería, Universidad Autónoma de Querétaro, Querétaro 76010, MéxicoFacultad de Ingeniería, Universidad Autónoma de Querétaro, Querétaro 76010, MéxicoFacultad de Ingeniería, Universidad Autónoma de Querétaro, Querétaro 76010, MéxicoFacultad de Ingeniería, Universidad Autónoma de Querétaro, Querétaro 76010, MéxicoFacultad de Ingeniería, Universidad Autónoma de Querétaro, Querétaro 76010, MéxicoFacultad de Ingeniería, Universidad Autónoma de Querétaro, Querétaro 76010, MéxicoQuality assessment of the resistance spot welding process (RSW) is vital during manufacturing. Evaluating the quality without altering the joint material’s physical and mechanical properties has gained interest. This study uses a trained computer vision model to propose a cheap, non-destructive quality-evaluation methodology. The methodology connects the welding input and during-process parameters with the output visual quality information. A manual resistance spot welding machine was used to monitor and record the process input and output parameters to generate the dataset for training. The welding current, welding time, and electrode pressure data were correlated with the welding spot nugget’s quality, mechanical characteristics, and thermal and visible images. Six machine learning models were trained on visible and thermographic images to classify the weld’s quality and connect the quality characteristics (pull force and welding diameter) and the manufacturing process parameters with the visible and thermographic images of the weld. Finally, a cross-validation method validated the robustness of these models. The results indicate that the welding time and the angle between electrodes are highly influential parameters on the mechanical strength of the joint. Additionally, models using visible images of the welding spot exhibited superior performance compared to thermal images.https://www.mdpi.com/1424-8220/25/6/1744resistance spot weldingelectrode forcewelding currentwelding timeconvolutional neural networkthermal images
spellingShingle Luis Alonso Domínguez-Molina
Edgar Rivas-Araiza
Juan Carlos Jauregui-Correa
Jose Luis Gonzalez-Cordoba
Jesús Carlos Pedraza-Ortega
Andras Takacs
Resistance Welding Quality Through Artificial Intelligence Techniques
Sensors
resistance spot welding
electrode force
welding current
welding time
convolutional neural network
thermal images
title Resistance Welding Quality Through Artificial Intelligence Techniques
title_full Resistance Welding Quality Through Artificial Intelligence Techniques
title_fullStr Resistance Welding Quality Through Artificial Intelligence Techniques
title_full_unstemmed Resistance Welding Quality Through Artificial Intelligence Techniques
title_short Resistance Welding Quality Through Artificial Intelligence Techniques
title_sort resistance welding quality through artificial intelligence techniques
topic resistance spot welding
electrode force
welding current
welding time
convolutional neural network
thermal images
url https://www.mdpi.com/1424-8220/25/6/1744
work_keys_str_mv AT luisalonsodominguezmolina resistanceweldingqualitythroughartificialintelligencetechniques
AT edgarrivasaraiza resistanceweldingqualitythroughartificialintelligencetechniques
AT juancarlosjaureguicorrea resistanceweldingqualitythroughartificialintelligencetechniques
AT joseluisgonzalezcordoba resistanceweldingqualitythroughartificialintelligencetechniques
AT jesuscarlospedrazaortega resistanceweldingqualitythroughartificialintelligencetechniques
AT andrastakacs resistanceweldingqualitythroughartificialintelligencetechniques