Journal of Powder Materials (한국분말재료학회지)

The Korean Powder Metallurgy & Materials Institute (한국분말재료학회 (*구 분말야금학회))
권호 표지
DOI QR코드

DOI QR Code

Characterization and Classification of Pores in Metal 3D Printing Materials with X-ray Tomography and Machine Learning

X-ray tomography 분석과 기계 학습을 활용한 금속 3D 프린팅 소재 내의 기공 형태 분류

  • Kim, Eun-Ah (3D printing materials research center, Korea Institute of Materials Science) ;
  • Kwon, Se-Hun (Materials Science and Engineering, Pusan national university) ;
  • Yang, Dong-Yeol (3D printing materials research center, Korea Institute of Materials Science) ;
  • Yu, Ji-Hun (3D printing materials research center, Korea Institute of Materials Science) ;
  • Kim, Kwon-Ill (C51) ;
  • Lee, Hak-Sung (3D printing materials research center, Korea Institute of Materials Science)
  • 김은아 (한국재료연구원 3D프린팅재료연구실) ;
  • 권세훈 (부산대학교 재료공학과) ;
  • 양동열 (한국재료연구원 3D프린팅재료연구실) ;
  • 유지훈 (한국재료연구원 3D프린팅재료연구실) ;
  • 김권일 ;
  • 이학성 (한국재료연구원 3D프린팅재료연구실)
  • Received : 2021.04.13
  • Accepted : 2021.06.07
  • Published : 2021.06.28
Download PDF
⟨ Previous Next ⟩

Abstract

Metal three-dimensional (3D) printing is an important emerging processing method in powder metallurgy. There are many successful applications of additive manufacturing. However, processing parameters such as laser power and scan speed must be manually optimized despite the development of artificial intelligence. Automatic calibration using information in an additive manufacturing database is desirable. In this study, 15 commercial pure titanium samples are processed under different conditions, and the 3D pore structures are characterized by X-ray tomography. These samples are easily classified into three categories, unmelted, well melted, or overmelted, depending on the laser energy density. Using more than 10,000 projected images for each category, convolutional neural networks are applied, and almost perfect classification of these samples is obtained. This result demonstrates that machine learning methods based on X-ray tomography can be helpful to automatically identify more suitable processing parameters.

Keywords

References

  1. Wohlers Report: 3D printing and Additive Manufacturing Global state of the Industry, Wohlers Associates, 25 (2020).
  2. Y. I. Kwon, M. C. Kang, Y. C. Kim, C. J. Bae and S. B. Lee: A Study on the 3D Printing Industry Revitalization Plan, KISTI (2021).
  3. S. M. H. Hojjatzadeh, N. D. Parab, W. Yan, Q. Guo, L. Xiong, C. Zhao, M. Qu, L. I. Escano, X. Xiao, K. Fezzaa, W. Everhart, T. Sun and L. Chen: Nat. Commun., 10 (2019) 3088. https://doi.org/10.1038/s41467-019-10973-9
  4. A. A. Martin, N. P. Calta, S. A. Khairallah, J. Wang, P. J. Depond, A. Y. Fong, V. Thampy, G. M. Guss, A. M. Kiss, K. H. Stone, C. J. Tassone, J. N. Weker, M. F. Toney, T. V. Buuren and M. J. Matthews: Nat. Commun., 10 (2019) 1987. https://doi.org/10.1038/s41467-019-10009-2
  5. C. L. A. Leung, S. Marussi, R. C. Atwood, M. Towrie, P. J. Withers and P. D. Lee: Nat. Commun., 9 (2018) 1355. https://doi.org/10.1038/s41467-018-03734-7
  6. H. S. Lee, D. K. Kim, Y. I. Kim, J. E. Nam, Y. Son, T. S. Kim and B. Lee: J. Korean Powder Metall. Inst., 27 (2020) 44. https://doi.org/10.4150/KPMI.2020.27.1.44
  7. C. Wang, X. P. Tan, S. B. Tor and C. S. Lim: Addit. Manuf., 36 (2020) 101538.
  8. B. Dutta and F. H. Froes: Additive Manufacturing of Titanium Alloys, Butterworth-Heinemann, (2016) 20.
  9. J. H. Hwang: J. Welding and Joining, 35 (2017) 29. https://doi.org/10.5781/JWJ.2017.35.4.5
  10. R. Boyer, G. Welsch and E. W. Collings: Materials Properties Handbook: Titanium Alloys, ASM International, (1994) 125.
  11. Y. S. Eom, D. W. Kim, K. T. Kim, S. S. Yang, J. H. Choe, I. J. Son and J. H. Yu: J. Korean Powder Metall. Inst., 27 (2020) 103. https://doi.org/10.4150/KPMI.2020.27.2.103
  12. https://github.com/macromancer/material_defect_detector/blob/master/preprocess_images.ipynb