Prediction of weld quality in laser welding of hardmetal and steel using high-speed imaging and machine learning methods
Laser welding of steel and hardmetal presents significant challenges due to their differing material properties. Improper laser welding parameters can result in unstable joints, ultimately leading to reduced mechanical strength of the weld. Therefore, defining an optimal process window is critical t...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | Journal of Advanced Joining Processes |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666330925000391 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850123763112214528 |
|---|---|
| author | Mohammadhossein Norouzian Mahan Khakpour Marko Orosnjak Atal Anil Kumar Slawomir Kedziora |
| author_facet | Mohammadhossein Norouzian Mahan Khakpour Marko Orosnjak Atal Anil Kumar Slawomir Kedziora |
| author_sort | Mohammadhossein Norouzian |
| collection | DOAJ |
| description | Laser welding of steel and hardmetal presents significant challenges due to their differing material properties. Improper laser welding parameters can result in unstable joints, ultimately leading to reduced mechanical strength of the weld. Therefore, defining an optimal process window is critical to ensuring weld quality. In addition, a continuous process monitoring method like High-Speed Imaging (HSI) is essential in real industrial applications to maintain stability and detect potential defects. Understanding plume dynamics helps identify the most important features of weld quality, but it also provides deeper insight into operational parameters that discriminate different weld types. Analysis of individual image plume frames from HSI reveals distinct statistical features that are identified as unique to each welding condition. Performing systematic feature selection using plume morphology, spatter generation and weld quality, we achieved>95 % leveraging Machine Learning (ML) classifiers. Particularly, Gradient Boosting Classifier (GBC), Linear Discriminant Analysis (LDA), Multinomial Logistic Regression (MNL-LR), Support Vector Machine (SVM), and Random Forest (RF), where the RF obtained >99 % classification accuracy of weld quality. The RF was then used in performing Recursive Feature Elimination (RFE), and with the robustness analysis, we managed to reduce the number of features from forty-nine to nine features while maintaining satisfactory performance (Accuracy = 0.981, F1-score = 0.961, AUROC = 0.997). The position of the weld plume, plume eccentricity and plume width are the most essential features that lead to the improvement of node purity and classification accuracy. |
| format | Article |
| id | doaj-art-6d453877b33e4032b000db70aec0954a |
| institution | OA Journals |
| issn | 2666-3309 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Advanced Joining Processes |
| spelling | doaj-art-6d453877b33e4032b000db70aec0954a2025-08-20T02:34:31ZengElsevierJournal of Advanced Joining Processes2666-33092025-06-011110031810.1016/j.jajp.2025.100318Prediction of weld quality in laser welding of hardmetal and steel using high-speed imaging and machine learning methodsMohammadhossein Norouzian0Mahan Khakpour1Marko Orosnjak2Atal Anil Kumar3Slawomir Kedziora4University of Luxembourg, 6, rue Coudenhove Kalergi, L-1359, Luxembourg; Corresponding author.University of Luxembourg, 6, rue Coudenhove Kalergi, L-1359, LuxembourgUniversity of Luxembourg, 6, rue Coudenhove Kalergi, L-1359, LuxembourgUniversité de Lorraine, Arts et Métiers ParisTech, LCFC, Metz, F-57000 Metz, FranceUniversity of Luxembourg, 6, rue Coudenhove Kalergi, L-1359, LuxembourgLaser welding of steel and hardmetal presents significant challenges due to their differing material properties. Improper laser welding parameters can result in unstable joints, ultimately leading to reduced mechanical strength of the weld. Therefore, defining an optimal process window is critical to ensuring weld quality. In addition, a continuous process monitoring method like High-Speed Imaging (HSI) is essential in real industrial applications to maintain stability and detect potential defects. Understanding plume dynamics helps identify the most important features of weld quality, but it also provides deeper insight into operational parameters that discriminate different weld types. Analysis of individual image plume frames from HSI reveals distinct statistical features that are identified as unique to each welding condition. Performing systematic feature selection using plume morphology, spatter generation and weld quality, we achieved>95 % leveraging Machine Learning (ML) classifiers. Particularly, Gradient Boosting Classifier (GBC), Linear Discriminant Analysis (LDA), Multinomial Logistic Regression (MNL-LR), Support Vector Machine (SVM), and Random Forest (RF), where the RF obtained >99 % classification accuracy of weld quality. The RF was then used in performing Recursive Feature Elimination (RFE), and with the robustness analysis, we managed to reduce the number of features from forty-nine to nine features while maintaining satisfactory performance (Accuracy = 0.981, F1-score = 0.961, AUROC = 0.997). The position of the weld plume, plume eccentricity and plume width are the most essential features that lead to the improvement of node purity and classification accuracy.http://www.sciencedirect.com/science/article/pii/S2666330925000391Laser weldingHardmetalSteelWeld quality predictionMachine learningHigh-speed imaging |
| spellingShingle | Mohammadhossein Norouzian Mahan Khakpour Marko Orosnjak Atal Anil Kumar Slawomir Kedziora Prediction of weld quality in laser welding of hardmetal and steel using high-speed imaging and machine learning methods Journal of Advanced Joining Processes Laser welding Hardmetal Steel Weld quality prediction Machine learning High-speed imaging |
| title | Prediction of weld quality in laser welding of hardmetal and steel using high-speed imaging and machine learning methods |
| title_full | Prediction of weld quality in laser welding of hardmetal and steel using high-speed imaging and machine learning methods |
| title_fullStr | Prediction of weld quality in laser welding of hardmetal and steel using high-speed imaging and machine learning methods |
| title_full_unstemmed | Prediction of weld quality in laser welding of hardmetal and steel using high-speed imaging and machine learning methods |
| title_short | Prediction of weld quality in laser welding of hardmetal and steel using high-speed imaging and machine learning methods |
| title_sort | prediction of weld quality in laser welding of hardmetal and steel using high speed imaging and machine learning methods |
| topic | Laser welding Hardmetal Steel Weld quality prediction Machine learning High-speed imaging |
| url | http://www.sciencedirect.com/science/article/pii/S2666330925000391 |
| work_keys_str_mv | AT mohammadhosseinnorouzian predictionofweldqualityinlaserweldingofhardmetalandsteelusinghighspeedimagingandmachinelearningmethods AT mahankhakpour predictionofweldqualityinlaserweldingofhardmetalandsteelusinghighspeedimagingandmachinelearningmethods AT markoorosnjak predictionofweldqualityinlaserweldingofhardmetalandsteelusinghighspeedimagingandmachinelearningmethods AT atalanilkumar predictionofweldqualityinlaserweldingofhardmetalandsteelusinghighspeedimagingandmachinelearningmethods AT slawomirkedziora predictionofweldqualityinlaserweldingofhardmetalandsteelusinghighspeedimagingandmachinelearningmethods |