Defect Detection Using Deep Learning-Based YOLOv3 in Cross-Sectional Image of Additive Manufacturing

• Autorzy: Choi Byungjoo , Choi Yongjun , Lee Moon-Gu , Kim Jung-Sub , Lee Sang-Won , Jeon Yongho

Identyfikatory

DOI

10.24425/amm.2021.136421

• Języki publikacji: EN

Abstrakty

EN

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.

Słowa kluczowe

EN

additive manufacturing; deposition defect; data augmentation; YOLOv3; object detection

• Wydawca: Institute of Metallurgy and Materials Science of Polish Academy of Sciences ; Committee of Materials Engineering and Metallurgy of Polish Academy of Sciences
• Czasopismo: Archives of Metallurgy and Materials
• Rocznik: 2021
• Tom: Vol. 66, iss. 4
• Strony: 1037--1041
• Opis fizyczny: Bibliogr. 15 poz., fot., rys., tab.

Twórcy

autor

Choi Byungjoo

• Ajou University, Department of Mechanical Engineering, 206, World Cup-ro, Yeongtong-gu, Suwon-si, Gyeonggi 16499, Republic of Korea

• https://orcid.org/0000-0002-1920-1158

autor

Choi Yongjun

• Ajou University, Department of Mechanical Engineering, 206, World Cup-ro, Yeongtong-gu, Suwon-si, Gyeonggi 16499, Republic of Korea

• https://orcid.org/0000-0003-4410-1076

autor

Lee Moon-Gu

• Ajou University, Department of Mechanical Engineering, 206, World Cup-ro, Yeongtong-gu, Suwon-si, Gyeonggi 16499, Republic of Korea

• https://orcid.org/0000-0002-1607-806X

autor

Kim Jung-Sub

• Sungkyunkwan University School of Mechanical Engineering, Suwon, Republic of Korea

• https://orcid.org/0000-0003-3342-3045

autor

Lee Sang-Won

• Sungkyunkwan University School of Mechanical Engineering, Suwon, Republic of Korea

• https://orcid.org/0000-0002-6352-5635

autor

Jeon Yongho

• Ajou University, Department of Mechanical Engineering, 206, World Cup-ro, Yeongtong-gu, Suwon-si, Gyeonggi 16499, Republic of Korea

• https://orcid.org/0000-0002-0183-8652

Bibliografia

• [1] O.H. Kwon, H.G. Kim, M.J. Ham, W.R. Kim, G.H. Kim, J.H. Cho, N.I. Kim, K.I. Kim, J. Intel. Manuf. 31, 375-386 (2020).
• [2] L. Scime, J. Beuth, Addit. Manuf. 24, 273-286 (2018).
• [3] L. Scime, J. Beuth, Addit. Manuf. 19, 114-126 (2018).
• [4] L. Scime, J. Beuth, Addit. Manuf. 25, 151-165 (2019).
• [5] L. Scime, J. Beuth, Addit. Manuf. 29, 100830, 1-9 (2019).
• [6] M. Khanzadeh, W. Tian, A. Yadollahi, H.R. Doude, M.A. Tschopp, Addit. Manuf. 23, 443-456 (2018).
• [7] M. Khanzadeh, S. Chowdhury, M. Marufuzzaman, M.A. Tschopp, L. Bian, J. Manuf. Syst. 47, 69-82 (2018).
• [8] M. Khanzadeh, S. Chowdhury, M.A. Tschopp, H.R. Doude, M. Marufuzzaman, L. Bian, Iise Trans. 51, 5, 437-455 (2019)
• [9] J. Redmon, A. Farhadi, Arxiv Preprint, 1804.02767 (2018).
• [10] https://imageai.readthedocs.io/en/latest/
• [11] https://github.com/tzutalin/labelimg
• [12] http://www.image-net.org/
• [13] https://imgaug.readthedocs.io/en/latest/index.html
• [14] J.S. Kim, B.J. Kang, S.W. Lee, J. Mech. Sci. Technol. 33, 12, 1-7 (2019).
• [15] A. Torralba, A.A. Efros, Proc. Cvprieee 12218709, 1521-1528 (2011).

Uwagi

1. This work was supported by the Korea Institute of Energy Technology Evaluation and Planning (KETEP) and the Ministry of Trade, Industry & Energy (MOTIE) of the Republic of Korea (No. 20206410100080).

2. Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).