دورية أكاديمية
Defect Detection Using Deep Learning-Based YOLOv3 in Cross-Sectional Image of Additive Manufacturing
| العنوان: | Defect Detection Using Deep Learning-Based YOLOv3 in Cross-Sectional Image of Additive Manufacturing |
|---|---|
| المؤلفون: | Byungjoo Choi, Yongjun Choi, Moon Gu Lee, Jung Sub Kim, Sang Won Lee, Yongho Jeon |
| المصدر: | Archives of Metallurgy and Materials, Vol vol. 66, Iss No 4, Pp 1037-1041 (2021) |
| بيانات النشر: | Polish Academy of Sciences, 2021. |
| سنة النشر: | 2021 |
| المجموعة: | LCC:Mining engineering. Metallurgy LCC:Materials of engineering and construction. Mechanics of materials |
| مصطلحات موضوعية: | additive manufacturing, deposition defect, data augmentation, yolov3, object detection, Mining engineering. Metallurgy, TN1-997, Materials of engineering and construction. Mechanics of materials, TA401-492 |
| الوصف: | Deposition defects like porosity, crack and lack of fusion in additive manufacturing process is a major obstacle to commercialization of the process. Thus, metallurgical microscopy analysis has been mainly conducted to optimize process conditions by detecting and investigating the defects. However, these defect detection methods indicate a deviation from the operator’s experience. In this study, artificial intelligence based YOLOv3 of object detection algorithm was applied to avoid the human dependency. The algorithm aims to automatically find and label the defects. To enable the aim, 80 training images and 20 verification images were prepared, and they were amplified into 640 training images and 160 verification images using augmentation algorithm of rotation, movement and scale down, randomly. To evaluate the performance of the algorithm, total loss was derived as the sum of localization loss, confidence loss, and classification loss. In the training process, the total loss was 8.672 for the initial 100 sample images. However, the total loss was reduced to 5.841 after training with additional 800 images. For the verification of the proposed method, new defect images were input and then the mean Average Precision (mAP) in terms of precision and recall was 0.3795. Therefore, the detection performance with high accuracy can be applied to industry for avoiding human errors. |
| نوع الوثيقة: | article |
| وصف الملف: | electronic resource |
| اللغة: | English |
| تدمد: | 2300-1909 |
| Relation: | https://journals.pan.pl/Content/119294/PDF/AMM-2021-4-23-Yongho%20Jeon.pdf; https://doaj.org/toc/2300-1909 |
| DOI: | 10.24425/amm.2021.136421 |
| URL الوصول: | https://doaj.org/article/74953c0e88d24db1a572278bd3f4b7a0 |
| رقم الأكسشن: | edsdoj.74953c0e88d24db1a572278bd3f4b7a0 |
| قاعدة البيانات: | Directory of Open Access Journals |
Full Text Finder | تدمد: | 23001909 |
|---|---|
| DOI: | 10.24425/amm.2021.136421 |