Automated Fillet Weld Inspection Based on Deep Learning from 2D Images

This work presents an automated welding inspection system based on a neural network trained through a series of 2D images of welding seams obtained in the same study. The object detection method follows a geometric deep learning model based on convolutional neural networks. Following an extensive re...

Full description

Saved in:
Bibliographic Details
Main Authors: Ignacio Diaz-Cano, Arturo Morgado-Estevez, José María Rodríguez Corral, Pablo Medina-Coello, Blas Salvador-Dominguez, Miguel Alvarez-Alcon
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/2/899
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832589190089408512
author Ignacio Diaz-Cano
Arturo Morgado-Estevez
José María Rodríguez Corral
Pablo Medina-Coello
Blas Salvador-Dominguez
Miguel Alvarez-Alcon
author_facet Ignacio Diaz-Cano
Arturo Morgado-Estevez
José María Rodríguez Corral
Pablo Medina-Coello
Blas Salvador-Dominguez
Miguel Alvarez-Alcon
author_sort Ignacio Diaz-Cano
collection DOAJ
description This work presents an automated welding inspection system based on a neural network trained through a series of 2D images of welding seams obtained in the same study. The object detection method follows a geometric deep learning model based on convolutional neural networks. Following an extensive review of available solutions, algorithms, and networks based on this convolutional strategy, it was determined that the You Only Look Once algorithm in its version 8 (YOLOv8) would be the most suitable for object detection due to its performance and features. Consequently, several models have been trained to enable the system to predict specific characteristics of weld beads. Firstly, the welding strategy used to manufacture the weld bead was predicted, distinguishing between two of them (Flux-Cored Arc Welding (FCAW)/Gas Metal Arc Welding (GMAW)), two of the predominant welding processes used in many industries, including shipbuilding, automotive, and aeronautics. In a subsequent experiment, the distinction between a well-manufactured weld bead and a defective one was predicted. In a final experiment, it was possible to predict whether a weld seam was well-manufactured or not, distinguishing between three possible welding defects. The study demonstrated high performance in three experiments, achieving top results in both binary classification (in the first two experiments) and multiclass classification (in the third experiment). The average prediction success rate exceeded 97% in all three experiments.
format Article
id doaj-art-6f43822b948748c2917561fb04c60739
institution Kabale University
issn 2076-3417
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-6f43822b948748c2917561fb04c607392025-01-24T13:21:15ZengMDPI AGApplied Sciences2076-34172025-01-0115289910.3390/app15020899Automated Fillet Weld Inspection Based on Deep Learning from 2D ImagesIgnacio Diaz-Cano0Arturo Morgado-Estevez1José María Rodríguez Corral2Pablo Medina-Coello3Blas Salvador-Dominguez4Miguel Alvarez-Alcon5Department of Computers Engineering, 11519 Cadiz, SpainDepartment of Automatic, Electronic, Computer Architecture & Communication Networks Engineering, 11519 Cadiz, SpainDepartment of Computers Engineering, 11519 Cadiz, SpainDepartment of Mechanical Engineering and Industrial Design, 11519 Cadiz, SpainDepartment of Automatic, Electronic, Computer Architecture & Communication Networks Engineering, 11519 Cadiz, SpainDepartment of Mechanical Engineering and Industrial Design, 11519 Cadiz, SpainThis work presents an automated welding inspection system based on a neural network trained through a series of 2D images of welding seams obtained in the same study. The object detection method follows a geometric deep learning model based on convolutional neural networks. Following an extensive review of available solutions, algorithms, and networks based on this convolutional strategy, it was determined that the You Only Look Once algorithm in its version 8 (YOLOv8) would be the most suitable for object detection due to its performance and features. Consequently, several models have been trained to enable the system to predict specific characteristics of weld beads. Firstly, the welding strategy used to manufacture the weld bead was predicted, distinguishing between two of them (Flux-Cored Arc Welding (FCAW)/Gas Metal Arc Welding (GMAW)), two of the predominant welding processes used in many industries, including shipbuilding, automotive, and aeronautics. In a subsequent experiment, the distinction between a well-manufactured weld bead and a defective one was predicted. In a final experiment, it was possible to predict whether a weld seam was well-manufactured or not, distinguishing between three possible welding defects. The study demonstrated high performance in three experiments, achieving top results in both binary classification (in the first two experiments) and multiclass classification (in the third experiment). The average prediction success rate exceeded 97% in all three experiments.https://www.mdpi.com/2076-3417/15/2/899CNNsurface inspection weldingshipbuildigFCAWGMAWwelding defects
spellingShingle Ignacio Diaz-Cano
Arturo Morgado-Estevez
José María Rodríguez Corral
Pablo Medina-Coello
Blas Salvador-Dominguez
Miguel Alvarez-Alcon
Automated Fillet Weld Inspection Based on Deep Learning from 2D Images
Applied Sciences
CNN
surface inspection welding
shipbuildig
FCAW
GMAW
welding defects
title Automated Fillet Weld Inspection Based on Deep Learning from 2D Images
title_full Automated Fillet Weld Inspection Based on Deep Learning from 2D Images
title_fullStr Automated Fillet Weld Inspection Based on Deep Learning from 2D Images
title_full_unstemmed Automated Fillet Weld Inspection Based on Deep Learning from 2D Images
title_short Automated Fillet Weld Inspection Based on Deep Learning from 2D Images
title_sort automated fillet weld inspection based on deep learning from 2d images
topic CNN
surface inspection welding
shipbuildig
FCAW
GMAW
welding defects
url https://www.mdpi.com/2076-3417/15/2/899
work_keys_str_mv AT ignaciodiazcano automatedfilletweldinspectionbasedondeeplearningfrom2dimages
AT arturomorgadoestevez automatedfilletweldinspectionbasedondeeplearningfrom2dimages
AT josemariarodriguezcorral automatedfilletweldinspectionbasedondeeplearningfrom2dimages
AT pablomedinacoello automatedfilletweldinspectionbasedondeeplearningfrom2dimages
AT blassalvadordominguez automatedfilletweldinspectionbasedondeeplearningfrom2dimages
AT miguelalvarezalcon automatedfilletweldinspectionbasedondeeplearningfrom2dimages