Junho Lee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Junho Lee has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Jae-Gil Jung
Division of Advanced Materials Engineering, Jeonbuk National University, Jeonju 54896, Republic of Korea
6 shared publications Seok-Jae Lee
4 shared publicationsSang-Hwa Lee
3 shared publications- Seonghyun Park
Jeonbuk National University, Division of Advanced Materials Engineering, Jeonju 54896, Republic of Korea
3 shared publications - Namhyuk Seo
Jeonbuk Technology Application Division, Korea Institute of Industrial Technology, Gimje 54325, Republic of Korea
2 shared publications - Seok-Jae Lee
Division of Advanced Materials Engineering, Jeonbuk National University, Jeonju 54896, Republic of Korea
2 shared publications
Latest Publications
- 6 July 2026
- Published by Elsevier in Intermetallics
- Vol. 197
Microstructural evolution and intermetallic phase formation in a high-pressure die-cast AlSi11MnFeMoZr alloy
- 6 July 2026
- Published by Elsevier in Intermetallics
- Vol. 197
Microstructural evolution and intermetallic phase formation in a high-pressure die-cast AlSi11MnFeMoZr alloy
- Open Access
Data-Driven Design of HPDC Aluminum Alloys Using Machine Learning and Inverse Design
This work proposes a data-driven design framework for high-pressure die-cast (HPDC) aluminum alloys that integrates robust data refinement, machine learning (ML) modeling, explainability, and inverse design. A total of 1237 tensile-test records from T5-aged HPDC alloys were aggregated into a curated dataset of 382 unique composition–heat-treatment combinations. Four regression models—Ridge regression, Random Forest (RF), XGBoost (XGB), and a multilayer perceptron (MLP)—were trained to predict yield strength (YS), ultimate tensile strength (UTS), and elongation (EL). Tree-based ensemble models (XGB and RF) achieved the highest accuracy and stability, capturing nonlinear interactions inherent to industrial HPDC data. In particular, the XGB model exhibited the best predictive performance, achieving test R2 values of 0.819 for UTS and 0.936 for EL, with corresponding RMSE values of 15.23 MPa and 1.112%, respectively. Feature-importance and SHapley Additive exPlanations (SHAP) analyses identified Mn, Si, Mg, Zn, and T5 aging temperature as the most influential variables, consistent with metallurgical considerations such as microstructural stabilization and precipitation strengthening. Finally, RF-based inverse design suggested new composition–process candidates satisfying UTS > 300 MPa and EL > 8%, a region scarcely represented in the experimental dataset. These results illustrate how interpretable ML can expand the feasible design space of HPDC aluminum alloys and support composition–process optimization in industrial applications.
Open AccessData-Driven Design of HPDC Aluminum Alloys Using Machine Learning and Inverse Design
This work proposes a data-driven design framework for high-pressure die-cast (HPDC) aluminum alloys that integrates robust data refinement, machine learning (ML) modeling, explainability, and inverse design. A total of 1237 tensile-test records from T5-aged HPDC alloys were aggregated into a curated dataset of 382 unique composition–heat-treatment combinations. Four regression models—Ridge regression, Random Forest (RF), XGBoost (XGB), and a multilayer perceptron (MLP)—were trained to predict yield strength (YS), ultimate tensile strength (UTS), and elongation (EL). Tree-based ensemble models (XGB and RF) achieved the highest accuracy and stability, capturing nonlinear interactions inherent to industrial HPDC data. In particular, the XGB model exhibited the best predictive performance, achieving test R2 values of 0.819 for UTS and 0.936 for EL, with corresponding RMSE values of 15.23 MPa and 1.112%, respectively. Feature-importance and SHapley Additive exPlanations (SHAP) analyses identified Mn, Si, Mg, Zn, and T5 aging temperature as the most influential variables, consistent with metallurgical considerations such as microstructural stabilization and precipitation strengthening. Finally, RF-based inverse design suggested new composition–process candidates satisfying UTS > 300 MPa and EL > 8%, a region scarcely represented in the experimental dataset. These results illustrate how interpretable ML can expand the feasible design space of HPDC aluminum alloys and support composition–process optimization in industrial applications.
- Open Access
- 13 December 2024
- Published by Elsevier in Journal of Materials Research and Technology
- Vol. 34, 738-747
Microstructural characterization of corrosion resistant Zn–15Al–6Mg–0.4Si galvanized coating
- 13 December 2024
- Published by Elsevier in Journal of Materials Research and Technology
- Vol. 34, 738-747
Open AccessMicrostructural characterization of corrosion resistant Zn–15Al–6Mg–0.4Si galvanized coating
- 15 August 2024
- Published by Elsevier in Materials Letters
- Vol. 375
Microstructural evolution and precipitation behavior of multicomponent Al83Mg5Si5Cu5Li2 alloy
- 15 August 2024
- Published by Elsevier in Materials Letters
- Vol. 375
Microstructural evolution and precipitation behavior of multicomponent Al83Mg5Si5Cu5Li2 alloy
- Open Access
- 13 June 2024
- Published by Elsevier in Journal of Materials Research and Technology
- Vol. 31, 205-212
Microstructural evolution and thermal stability of Al–Zn–Mg–Cu–Si–Zr alloy fabricated via spark plasma sintering
- 13 June 2024
- Published by Elsevier in Journal of Materials Research and Technology
- Vol. 31, 205-212
Open AccessMicrostructural evolution and thermal stability of Al–Zn–Mg–Cu–Si–Zr alloy fabricated via spark plasma sintering
- 10 April 2024
- Published by Polish Academy of Sciences Chancellery in Archives of Metallurgy and Materials
- Vol. 69 (1) , 145-149
Effect of Al–5Ti–1B Addition on Solidification Microstructure and Hot Deformation Behavior of DC-Cast Al–Zn–Mg–Cu Alloy
This study investigated the effect of adding Al–5Ti–1B grain refiner on the solidification microstructure and hot deformation behavior of direct-chill (DC) cast Al–Zn–Mg–Cu alloys. The grain refiner significantly decreased the grain size and modified the morphology. Fine-grained (FG) alloys with grain refiners exhibit coarse secondary phases with a reduced number density compared to coarse-grained (CG) alloys without grain refiners. Dynamic recrystallization (DRX) was enhanced at higher compression temperatures and lower strain rates in the CG and FG alloys. Both particle stimulated nucleation (PSN) and continuous dynamic recrystallization (CDRX) are enhanced in the FG alloys, resulting in decreased peak stress values (indicating DRX onset) at 450°C. The peak stress of the FG alloys was higher at 300-400°C than that of the CG alloys because of grain refinement hardening over softening by enhanced DRX.
- 10 April 2024
- Published by Polish Academy of Sciences Chancellery in Archives of Metallurgy and Materials
- Vol. 69 (1) , 145-149
Effect of Al–5Ti–1B Addition on Solidification Microstructure and Hot Deformation Behavior of DC-Cast Al–Zn–Mg–Cu Alloy
This study investigated the effect of adding Al–5Ti–1B grain refiner on the solidification microstructure and hot deformation behavior of direct-chill (DC) cast Al–Zn–Mg–Cu alloys. The grain refiner significantly decreased the grain size and modified the morphology. Fine-grained (FG) alloys with grain refiners exhibit coarse secondary phases with a reduced number density compared to coarse-grained (CG) alloys without grain refiners. Dynamic recrystallization (DRX) was enhanced at higher compression temperatures and lower strain rates in the CG and FG alloys. Both particle stimulated nucleation (PSN) and continuous dynamic recrystallization (CDRX) are enhanced in the FG alloys, resulting in decreased peak stress values (indicating DRX onset) at 450°C. The peak stress of the FG alloys was higher at 300-400°C than that of the CG alloys because of grain refinement hardening over softening by enhanced DRX.