Prediction of Weld Geometry in Laser Overlap Welding of Low-Carbon Galvanized Steel

Accurate prediction of weld bead geometry is critical for optimizing laser overlap welding of low-carbon galvanized steel, as it directly affects joint quality and mechanical performance. Traditional finite element method (FEM)-based models provide reliable predictions but are computationally expens...

Full description

Saved in:
Bibliographic Details
Main Authors: Kamel Oussaid, Narges Omidi, Abderrazak El Ouafi, Noureddine Barka
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Metals
Subjects:
Online Access:https://www.mdpi.com/2075-4701/15/4/447
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849713767006339072
author Kamel Oussaid
Narges Omidi
Abderrazak El Ouafi
Noureddine Barka
author_facet Kamel Oussaid
Narges Omidi
Abderrazak El Ouafi
Noureddine Barka
author_sort Kamel Oussaid
collection DOAJ
description Accurate prediction of weld bead geometry is critical for optimizing laser overlap welding of low-carbon galvanized steel, as it directly affects joint quality and mechanical performance. Traditional finite element method (FEM)-based models provide reliable predictions but are computationally expensive and impractical for real-time applications. This study presents an artificial neural network (ANN)-based predictive model trained on a combination of experimental data and validated FEM simulations to estimate key weld characteristics, including depth of penetration (DOP), weld bead width at the surface (WS), and weld bead width at the interface (WI). The ANN model was evaluated using various improved statistical metrics. Results demonstrated a strong correlation between ANN predictions and experimental measurements, with R<sup>2</sup> values exceeding 95% for WS and DOP and 92% for WI, and mean errors below 7%. A comparative analysis between ANN, FEM, and experimental data confirmed the model’s reliability across different welding conditions. Additionally, ANN significantly reduced computational time compared to FEM while maintaining high accuracy, making it a practical tool for real-time process optimization. These findings highlight the potential of ANN models as efficient alternatives to conventional simulation techniques in laser overlap welding applications. Future improvements may involve integrating real-time sensor data and deep learning techniques to further enhance predictive performance.
format Article
id doaj-art-84688e81a3da4e58a3ae7eafa926bf4e
institution DOAJ
issn 2075-4701
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Metals
spelling doaj-art-84688e81a3da4e58a3ae7eafa926bf4e2025-08-20T03:13:52ZengMDPI AGMetals2075-47012025-04-0115444710.3390/met15040447Prediction of Weld Geometry in Laser Overlap Welding of Low-Carbon Galvanized SteelKamel Oussaid0Narges Omidi1Abderrazak El Ouafi2Noureddine Barka3Department of Mathematics, Computer Science and Engineering, Université du Québec à Rimouski, Rimouski, QC G5L 3A1, CanadaDepartment of Mathematics, Computer Science and Engineering, Université du Québec à Rimouski, Rimouski, QC G5L 3A1, CanadaDepartment of Mathematics, Computer Science and Engineering, Université du Québec à Rimouski, Rimouski, QC G5L 3A1, CanadaDepartment of Mathematics, Computer Science and Engineering, Université du Québec à Rimouski, Rimouski, QC G5L 3A1, CanadaAccurate prediction of weld bead geometry is critical for optimizing laser overlap welding of low-carbon galvanized steel, as it directly affects joint quality and mechanical performance. Traditional finite element method (FEM)-based models provide reliable predictions but are computationally expensive and impractical for real-time applications. This study presents an artificial neural network (ANN)-based predictive model trained on a combination of experimental data and validated FEM simulations to estimate key weld characteristics, including depth of penetration (DOP), weld bead width at the surface (WS), and weld bead width at the interface (WI). The ANN model was evaluated using various improved statistical metrics. Results demonstrated a strong correlation between ANN predictions and experimental measurements, with R<sup>2</sup> values exceeding 95% for WS and DOP and 92% for WI, and mean errors below 7%. A comparative analysis between ANN, FEM, and experimental data confirmed the model’s reliability across different welding conditions. Additionally, ANN significantly reduced computational time compared to FEM while maintaining high accuracy, making it a practical tool for real-time process optimization. These findings highlight the potential of ANN models as efficient alternatives to conventional simulation techniques in laser overlap welding applications. Future improvements may involve integrating real-time sensor data and deep learning techniques to further enhance predictive performance.https://www.mdpi.com/2075-4701/15/4/447laser overlap weldinglow-carbon galvanized steelweld bead geometryartificial neural networkpredictive modelingfinite element method
spellingShingle Kamel Oussaid
Narges Omidi
Abderrazak El Ouafi
Noureddine Barka
Prediction of Weld Geometry in Laser Overlap Welding of Low-Carbon Galvanized Steel
Metals
laser overlap welding
low-carbon galvanized steel
weld bead geometry
artificial neural network
predictive modeling
finite element method
title Prediction of Weld Geometry in Laser Overlap Welding of Low-Carbon Galvanized Steel
title_full Prediction of Weld Geometry in Laser Overlap Welding of Low-Carbon Galvanized Steel
title_fullStr Prediction of Weld Geometry in Laser Overlap Welding of Low-Carbon Galvanized Steel
title_full_unstemmed Prediction of Weld Geometry in Laser Overlap Welding of Low-Carbon Galvanized Steel
title_short Prediction of Weld Geometry in Laser Overlap Welding of Low-Carbon Galvanized Steel
title_sort prediction of weld geometry in laser overlap welding of low carbon galvanized steel
topic laser overlap welding
low-carbon galvanized steel
weld bead geometry
artificial neural network
predictive modeling
finite element method
url https://www.mdpi.com/2075-4701/15/4/447
work_keys_str_mv AT kameloussaid predictionofweldgeometryinlaseroverlapweldingoflowcarbongalvanizedsteel
AT nargesomidi predictionofweldgeometryinlaseroverlapweldingoflowcarbongalvanizedsteel
AT abderrazakelouafi predictionofweldgeometryinlaseroverlapweldingoflowcarbongalvanizedsteel
AT noureddinebarka predictionofweldgeometryinlaseroverlapweldingoflowcarbongalvanizedsteel