AN INDUSTRIAL INSPECTION APPROACH FOR WELD DEFECTS USING MACHINE LEARNING ALGORITHM
The weld defects are formed due to the incorrect welding patterns or wrong welding process. The defects in the weld may vary from size, shape and their projected quality. The most common weld defects occur during welding process is slag inclusions, porosity, lack of fusion and incomplete penetration...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
XLESCIENCE
2019-06-01
|
| Series: | International Journal of Advances in Signal and Image Sciences |
| Subjects: | |
| Online Access: | https://xlescience.org/index.php/IJASIS/article/view/38 |
| _version_ | 1818042743958536192 |
|---|---|
| author | Kalai Selvi V John Aravindar D |
| author_facet | Kalai Selvi V John Aravindar D |
| author_sort | Kalai Selvi V |
| collection | DOAJ |
| description | The weld defects are formed due to the incorrect welding patterns or wrong welding process. The defects in the weld may vary from size, shape and their projected quality. The most common weld defects occur during welding process is slag inclusions, porosity, lack of fusion and incomplete penetration. In this study, an effective method for weld defect classification using machine learning algorithm is presented. The system uses Speeded-up Robust Features (SURF) for feature extraction and one of the machine learning algorithms called Auto-Encoder Classifier (AEC) for classification. Initially, the features that distinguish weld defects and no defects in the weld image are extracted by SURF. Then, AEC is analyzed for weld image classification using different number of neurons in different hidden layers (2 and 3 hidden layers). The performance of the system is evaluated by GD X-ray weld image database. The results show that the weld images are correctly classified with 98% accuracy using SURF and AEC. |
| first_indexed | 2024-12-10T08:51:11Z |
| format | Article |
| id | doaj.art-ee200afa47a0472bb52530b062a41904 |
| institution | Directory Open Access Journal |
| issn | 2457-0370 |
| language | English |
| last_indexed | 2024-12-10T08:51:11Z |
| publishDate | 2019-06-01 |
| publisher | XLESCIENCE |
| record_format | Article |
| series | International Journal of Advances in Signal and Image Sciences |
| spelling | doaj.art-ee200afa47a0472bb52530b062a419042022-12-22T01:55:34ZengXLESCIENCEInternational Journal of Advances in Signal and Image Sciences2457-03702019-06-0151152110.29284/ijasis.5.1.2019.15-2138AN INDUSTRIAL INSPECTION APPROACH FOR WELD DEFECTS USING MACHINE LEARNING ALGORITHMKalai Selvi VJohn Aravindar DThe weld defects are formed due to the incorrect welding patterns or wrong welding process. The defects in the weld may vary from size, shape and their projected quality. The most common weld defects occur during welding process is slag inclusions, porosity, lack of fusion and incomplete penetration. In this study, an effective method for weld defect classification using machine learning algorithm is presented. The system uses Speeded-up Robust Features (SURF) for feature extraction and one of the machine learning algorithms called Auto-Encoder Classifier (AEC) for classification. Initially, the features that distinguish weld defects and no defects in the weld image are extracted by SURF. Then, AEC is analyzed for weld image classification using different number of neurons in different hidden layers (2 and 3 hidden layers). The performance of the system is evaluated by GD X-ray weld image database. The results show that the weld images are correctly classified with 98% accuracy using SURF and AEC.https://xlescience.org/index.php/IJASIS/article/view/38x-ray weld images, weld image classification, speeded-up robust features, machine learning, auto-encoder classifier |
| spellingShingle | Kalai Selvi V John Aravindar D AN INDUSTRIAL INSPECTION APPROACH FOR WELD DEFECTS USING MACHINE LEARNING ALGORITHM International Journal of Advances in Signal and Image Sciences x-ray weld images, weld image classification, speeded-up robust features, machine learning, auto-encoder classifier |
| title | AN INDUSTRIAL INSPECTION APPROACH FOR WELD DEFECTS USING MACHINE LEARNING ALGORITHM |
| title_full | AN INDUSTRIAL INSPECTION APPROACH FOR WELD DEFECTS USING MACHINE LEARNING ALGORITHM |
| title_fullStr | AN INDUSTRIAL INSPECTION APPROACH FOR WELD DEFECTS USING MACHINE LEARNING ALGORITHM |
| title_full_unstemmed | AN INDUSTRIAL INSPECTION APPROACH FOR WELD DEFECTS USING MACHINE LEARNING ALGORITHM |
| title_short | AN INDUSTRIAL INSPECTION APPROACH FOR WELD DEFECTS USING MACHINE LEARNING ALGORITHM |
| title_sort | industrial inspection approach for weld defects using machine learning algorithm |
| topic | x-ray weld images, weld image classification, speeded-up robust features, machine learning, auto-encoder classifier |
| url | https://xlescience.org/index.php/IJASIS/article/view/38 |
| work_keys_str_mv | AT kalaiselviv anindustrialinspectionapproachforwelddefectsusingmachinelearningalgorithm AT johnaravindard anindustrialinspectionapproachforwelddefectsusingmachinelearningalgorithm AT kalaiselviv industrialinspectionapproachforwelddefectsusingmachinelearningalgorithm AT johnaravindard industrialinspectionapproachforwelddefectsusingmachinelearningalgorithm |