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
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
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.
Abstract
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.
참고문헌 (27)
- J. Fiocchi, , Mater. Des, 204, pp.109651~ (2021)
- W. Li, , Mater. Sci. Eng. A, 663, pp.116~ (2016)
- L. Girelli, , Mater. Sci. Eng. A, 739, pp.317~ (2019)
- Q. Han, , Int. J. Adv. Manuf. Technol, 102, pp.3315~ (2019)
- L. Zhou, , Mater. Charact, 143, pp.5~ (2018)
- K. Zygula, , World Sci. News, 104, pp.456~ (2018)
- E. Padovano, , J. Alloys Compd, 831, pp.154822~ (2020)
- P. Delroisse, , Scr. Mater, 141, pp.32~ (2017)
- W. H. Kan, , Addit. Manuf, 29, pp.100805~ (2019)
- S. Bagherifard, , Mater. Des, 145, pp.28~ (2018)
- C. D. Clement, , J. Manuf. Mater. Process, 6, pp.52~ (2022)
- J. Jeon, , J. Mater. Res. Technol, 21, pp.1408~ (2022)
- C. Yang, , Acta Mater, 222, pp.117431~ (2022)
- Titus Thankachan, "Machine Learning and Statistical Approach to Predict and Analyze Wear Rates in Copper Surface Composites", Metals and Materials International, 27(2), pp.220~234 (2021), 대한금속·재료학회[DOI]
- Daegeun Hong, "Exploration of Machine Learning to Predict Hot Ductility of Cast Steel from Chemical Composition and Thermal Conditions", Metals and Materials International, 27(2), pp.298~305 (2021), 대한금속·재료학회[DOI]
- J. Jeon, , J. Mater. Res. Technol, 16, pp.129~ (2022)
- 전준협, "기계학습 모델 복잡도에 따른 템퍼드 마르텐사이트 경도 예측 정확도 비교 연구", 대한금속·재료학회지, 60(9), pp.713~721 (2022), 대한금속·재료학회[DOI]
- Yun Zhang, "Lattice Misfit Predictions via the Gaussian Process Regression for Ni-Based Single Crystal Superalloys", Metals and Materials International, 27(2), pp.235~253 (2021), 대한금속·재료학회[DOI]
- C. Capdevila, , ISIJ Int, 42, pp.894~ (2002)
- J. Jeon, , Mater. Trans, 63, pp.1369~ (2022)
- J. Jeon, , J. Mater. Sci, 57, pp.18142~ (2022)
- J. Jeon, , Metals, 11, pp.1159~ (2021)
- J. Jeon, , Metals, 11, pp.729~ (2021)
- S. K. Murthy, , J. Artif. Intell. Res, 2, pp.1~ (1994)
- Q. R. Wang, , IEEE Trans. Pattern Anal. Mach. Intell, PAMI-6, pp.406~ (1984)
- A. J. Smola, , Stat. Comput, 14, pp.199~ (2004)
- T. M. Cover, , IEEE Trans. Inf. Theory, 13, pp.21~ (1967)