Automated Categorization of Multiclass Welding Defects Using the X-ray Image Augmentation and Convolutional Neural Network
The detection of weld defects by using X-rays is an important task in the industry. It requires trained specialists with the expertise to conduct a timely inspection, which is costly and cumbersome. Moreover, the process can be erroneous due to fatigue and lack of concentration. In this context, thi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/14/6422 |
| _version_ | 1827731814446268416 |
|---|---|
| author | Dalila Say Salah Zidi Saeed Mian Qaisar Moez Krichen |
| author_facet | Dalila Say Salah Zidi Saeed Mian Qaisar Moez Krichen |
| author_sort | Dalila Say |
| collection | DOAJ |
| description | The detection of weld defects by using X-rays is an important task in the industry. It requires trained specialists with the expertise to conduct a timely inspection, which is costly and cumbersome. Moreover, the process can be erroneous due to fatigue and lack of concentration. In this context, this study proposes an automated approach to identify multi-class welding defects by processing the X-ray images. It is realized by an intelligent hybridization of the data augmentation techniques and convolutional neural network (CNN). The proposed data augmentation mainly performs random rotation, shearing, zooming, brightness adjustment, and horizontal flips on the intended images. This augmentation is beneficial for the realization of a generalized trained CNN model, which can process the multi-class dataset for the identification of welding defects. The effectiveness of the proposed method is confirmed by testing its performance in processing an industrial dataset. The intended dataset contains 4479 X-ray images and belongs to six groups: cavity, cracks, inclusion slag, lack of fusion, shape defects, and normal defects. The devised technique achieved an average accuracy of 92%. This indicates that the approach is promising and can be used in contemporary solutions for the automated detection and categorization of welding defects. |
| first_indexed | 2024-03-11T00:39:50Z |
| format | Article |
| id | doaj.art-335936fb897843dd8c5d3aa59235f1c8 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T00:39:50Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-335936fb897843dd8c5d3aa59235f1c82023-11-18T21:17:30ZengMDPI AGSensors1424-82202023-07-012314642210.3390/s23146422Automated Categorization of Multiclass Welding Defects Using the X-ray Image Augmentation and Convolutional Neural NetworkDalila Say0Salah Zidi1Saeed Mian Qaisar2Moez Krichen3Hatem Bettaher Laboratory, IResCoMath, University of Gabes, Gabes 6029, TunisiaHatem Bettaher Laboratory, IResCoMath, University of Gabes, Gabes 6029, TunisiaCESI LINEACT, 69100 Lyon, FranceFaculty of Computer Science and Information Technology, Al-Baha University, Al-Baha 65528, Saudi ArabiaThe detection of weld defects by using X-rays is an important task in the industry. It requires trained specialists with the expertise to conduct a timely inspection, which is costly and cumbersome. Moreover, the process can be erroneous due to fatigue and lack of concentration. In this context, this study proposes an automated approach to identify multi-class welding defects by processing the X-ray images. It is realized by an intelligent hybridization of the data augmentation techniques and convolutional neural network (CNN). The proposed data augmentation mainly performs random rotation, shearing, zooming, brightness adjustment, and horizontal flips on the intended images. This augmentation is beneficial for the realization of a generalized trained CNN model, which can process the multi-class dataset for the identification of welding defects. The effectiveness of the proposed method is confirmed by testing its performance in processing an industrial dataset. The intended dataset contains 4479 X-ray images and belongs to six groups: cavity, cracks, inclusion slag, lack of fusion, shape defects, and normal defects. The devised technique achieved an average accuracy of 92%. This indicates that the approach is promising and can be used in contemporary solutions for the automated detection and categorization of welding defects.https://www.mdpi.com/1424-8220/23/14/6422CNNdeep learningmulti-class classificationdata augmentationwelding defectssegmentation |
| spellingShingle | Dalila Say Salah Zidi Saeed Mian Qaisar Moez Krichen Automated Categorization of Multiclass Welding Defects Using the X-ray Image Augmentation and Convolutional Neural Network Sensors CNN deep learning multi-class classification data augmentation welding defects segmentation |
| title | Automated Categorization of Multiclass Welding Defects Using the X-ray Image Augmentation and Convolutional Neural Network |
| title_full | Automated Categorization of Multiclass Welding Defects Using the X-ray Image Augmentation and Convolutional Neural Network |
| title_fullStr | Automated Categorization of Multiclass Welding Defects Using the X-ray Image Augmentation and Convolutional Neural Network |
| title_full_unstemmed | Automated Categorization of Multiclass Welding Defects Using the X-ray Image Augmentation and Convolutional Neural Network |
| title_short | Automated Categorization of Multiclass Welding Defects Using the X-ray Image Augmentation and Convolutional Neural Network |
| title_sort | automated categorization of multiclass welding defects using the x ray image augmentation and convolutional neural network |
| topic | CNN deep learning multi-class classification data augmentation welding defects segmentation |
| url | https://www.mdpi.com/1424-8220/23/14/6422 |
| work_keys_str_mv | AT dalilasay automatedcategorizationofmulticlassweldingdefectsusingthexrayimageaugmentationandconvolutionalneuralnetwork AT salahzidi automatedcategorizationofmulticlassweldingdefectsusingthexrayimageaugmentationandconvolutionalneuralnetwork AT saeedmianqaisar automatedcategorizationofmulticlassweldingdefectsusingthexrayimageaugmentationandconvolutionalneuralnetwork AT moezkrichen automatedcategorizationofmulticlassweldingdefectsusingthexrayimageaugmentationandconvolutionalneuralnetwork |