DOI QR코드

DOI QR Code

레이저 분말 베드 용융법으로 제조된 AlSi10Mg 합금의 경도 예측을 위한 설명 가능한 인공지능 활용

Application of Explainable Artificial Intelligence for Predicting Hardness of AlSi10Mg Alloy Manufactured by Laser Powder Bed Fusion

  • 전준협 (전북대학교 신소재공학부) ;
  • 서남혁 (전북대학교 신소재공학부) ;
  • 김민수 (한국생산기술연구원 탄소경량소재응용그룹) ;
  • 손승배 (전북대학교 신소재공학부) ;
  • 정재길 (전북대학교 신소재공학부) ;
  • 이석재 (전북대학교 신소재공학부)
  • Junhyub Jeon (Department of Metallurgical Engineering, Jeonbuk National University) ;
  • Namhyuk Seo (Department of Metallurgical Engineering, Jeonbuk National University) ;
  • Min-Su Kim (Jeonbuk Regional Division, Korea Institute of Industrial Technology) ;
  • Seung Bae Son (Department of Metallurgical Engineering, Jeonbuk National University) ;
  • Jae-Gil Jung (Department of Metallurgical Engineering, Jeonbuk National University) ;
  • Seok-Jae Lee (Department of Metallurgical Engineering, Jeonbuk National University)
  • 투고 : 2023.06.08
  • 심사 : 2023.06.24
  • 발행 : 2023.06.28

초록

In this study, machine learning models are proposed to predict the Vickers hardness of AlSi10Mg alloys fabricated by laser powder bed fusion (LPBF). A total of 113 utilizable datasets were collected from the literature. The hyperparameters of the machine-learning models were adjusted to select an accurate predictive model. The random forest regression (RFR) model showed the best performance compared to support vector regression, artificial neural networks, and k-nearest neighbors. The variable importance and prediction mechanisms of the RFR were discussed by Shapley additive explanation (SHAP). Aging time had the greatest influence on the Vickers hardness, followed by solution time, solution temperature, layer thickness, scan speed, power, aging temperature, average particle size, and hatching distance. Detailed prediction mechanisms for RFR are analyzed using SHAP dependence plots.

키워드

과제정보

This work was supported by a Korea Institute for Advancement of Technology grant, funded by the Korea Government (MOTIE) (P0002019), as part of the Competency Development Program for Industry Specialists. And also this work was supported by the Technology Innovation Program (20010408) funded by the Ministry of Trade, Industry & Energy (MOTIE, Korea).

참고문헌

  1. J. Fiocchi, A. Tuissi and C. A. Biffi: Mater. Des., 204 (2021) 109651.
  2. W. Li, S. Li, J. Liu, A. Zhang, Y. Zhou, Q. Wei, C. Yan and Y. Shi: Mater. Sci. Eng. A, 663 (2016) 116.
  3. L. Girelli, M. Tocci, M. Gelfi and A. Pola: Mater. Sci. Eng. A, 739 (2019) 317.
  4. Q. Han and Y. Jiao: Int. J. Adv. Manuf. Technol., 102 (2019) 3315.
  5. L. Zhou, A. Mehta, E. Schulz, B. McWilliams, K. Cho and Y. Sohn: Mater. Charact., 143 (2018) 5.
  6. K. Zygula, B. Nosek, H. Pasiowiec and N. Szysiak: World Sci. News, 104 (2018) 456.
  7. E. Padovano, C. Badini, A. Pantarelli, F. Gili and F. D'Aiuto: J. Alloys Compd., 831 (2020) 154822.
  8. P. Delroisse, P. J. Jacques, E. Maire, O. Rigo and A. Simar: Scr. Mater., 141 (2017) 32.
  9. W. H. Kan, Y. Nadot, M. Foley, L. Ridosz, G. Proust and J. M. Cairney: Addit. Manuf., 29 (2019) 100805.
  10. S. Bagherifard, N. Beretta, S. Monti, M. Riccio, M. Bandini and M. Guagliano: Mater. Des., 145 (2018) 28.
  11. C. D. Clement, J. Masson and A. S. Kabir: J. Manuf. Mater. Process., 6 (2022) 52.
  12. J. Jeon, N. Seo, J.-G. Jung, H.-S. Kim, S. B. Son and S.-J. Lee: J. Mater. Res. Technol., 21 (2022) 1408.
  13. C. Yang, C. Ren, Y. Jia, G. Wang, M. Li and W. Lu: Acta Mater., 222 (2022) 117431.
  14. T. Thankachan, K. S. Prakash, V. Kavimani and S. R. Silambarasan: Met. Mater. Int., 27 (2021) 220.
  15. D. Hong, S. Kwon and C. Yim: Met. Mater. Int., 27 (2021) 298.
  16. J. Jeon, G. Kim, N. Seo, H. Choi, H.-J. Kim, M.-H. Lee, H.-K. Lim, S. B. Son and S.-J. Lee: J. Mater. Res. Technol., 16 (2022) 129.
  17. J. Jeon, D. Kim, J.-H. Hong, H.-J. Kim and S.-J. Lee: Korean J. Met. Mater., 60 (2022) 713.
  18. Y. Zhang and X. Xu: Met. Mater. Int., 27 (2021) 235.
  19. C. Capdevila, F. G. Caballero and C. Garcia de Andres: ISIJ Int., 42 (2002) 894.
  20. J. Jeon, N. Seo, J.-G. Jung, S. B. Son and S.-J. Lee: Mater. Trans., 63 (2022) 1369.
  21. J. Jeon, N. Seo, S. B. Son, J.-G. Jung and S.-J. Lee: J. Mater. Sci., 57 (2022) 18142.
  22. J. Jeon, N. Seo, S. B. Son, S.-J. Lee and M. Jung: Metals, 11 (2021) 1159.
  23. J. Jeon, N. Seo, H.-J. Kim, M.-H. Lee, H.-K. Lim, S. B. Son and S.-J. Lee: Metals, 11 (2021) 729.
  24. S. K. Murthy, S. Kasif and S. Salzberg: J. Artif. Intell. Res., 2 (1994) 1.
  25. Q. R. Wang and C. Y. Suen: IEEE Trans. Pattern Anal. Mach. Intell., PAMI-6 (1984) 406.
  26. A. J. Smola and B. Scholkopf: Stat. Comput., 14 (2004) 199.
  27. T. M. Cover and P. E. Hart: IEEE Trans. Inf. Theory, 13 (1967) 21.