Bong-Chun Lee
Bong-Chun Lee has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Jiseok Seo
Korea Conformity Laboratory (KCL), Daejeon & Chungnam Center, 26-34 Gajeongbuk-ro, Yuseong-gu, Daejeon 34113, Republic of Korea
1 shared publication - Jun Lee
Korea Conformity Laboratory (KCL), Daejeon & Chungnam Center, 26-34 Gajeongbuk-ro, Yuseong-gu, Daejeon 34113, Republic of Korea
1 shared publication - Kwang-Min Park
Construction Technology Research Centre, Construction Division, Korea Conformity Laboratories, Seoul 08503, Republic of Korea
1 shared publication - Kyung-Sung Min
Construction Technology Research Centre, Construction Division, Korea Conformity Laboratories, Seoul 08503, Korea
1 shared publication - Young-Sook Roh
School of Architecture, Seoul National University of Science and Technology, Seoul, Republic of Korea
1 shared publication
Latest Publications
- Open Access
Automated Evaluation of Layer Thickness Uniformity in 3D-Printed Cementitious Composites Using Deep Learning and Comparison with Manual Tracing Methods
Layer thickness uniformity critically influences the dimensional accuracy and mechanical performance of large-scale cementitious structures produced by material extrusion 3D printing. This study introduces a computer vision workflow that couples traditional preprocessing with a ResNet-50 convolutional neural network to automatically detect interlayer boundaries and quantify thickness variation. Hollow 50 × 50 × 50 mm specimens, printed from mixes optimized by void ratio (0.6–0.7) for fluidity and stackability, supplied 25 labeled RGB images for training and validation. The network achieved 96% training and 95% validation accuracy, generating boundary maps that required minimal linear interpolation. Pixel-based analysis yielded uniformity indices of 0.857–0.924, closely matching those from manual tracing (0.819–0.919) but with smaller standard deviations, indicating higher measurement stability and reduced sensitivity to lighting artifacts. The proposed method therefore provides an objective, reproducible alternative to labor-intensive manual evaluation and supports real-time prediction and control of dimensional errors during construction-scale 3D printing, advancing the precision and industrial applicability of additive manufacturing with cementitious composites. However, since this study was conducted under limited variable conditions, such as a simplified and repetitive experimental environment, a larger number of images will be required for model training to enable application under more general conditions.
Open AccessAutomated Evaluation of Layer Thickness Uniformity in 3D-Printed Cementitious Composites Using Deep Learning and Comparison with Manual Tracing Methods
Layer thickness uniformity critically influences the dimensional accuracy and mechanical performance of large-scale cementitious structures produced by material extrusion 3D printing. This study introduces a computer vision workflow that couples traditional preprocessing with a ResNet-50 convolutional neural network to automatically detect interlayer boundaries and quantify thickness variation. Hollow 50 × 50 × 50 mm specimens, printed from mixes optimized by void ratio (0.6–0.7) for fluidity and stackability, supplied 25 labeled RGB images for training and validation. The network achieved 96% training and 95% validation accuracy, generating boundary maps that required minimal linear interpolation. Pixel-based analysis yielded uniformity indices of 0.857–0.924, closely matching those from manual tracing (0.819–0.919) but with smaller standard deviations, indicating higher measurement stability and reduced sensitivity to lighting artifacts. The proposed method therefore provides an objective, reproducible alternative to labor-intensive manual evaluation and supports real-time prediction and control of dimensional errors during construction-scale 3D printing, advancing the precision and industrial applicability of additive manufacturing with cementitious composites. However, since this study was conducted under limited variable conditions, such as a simplified and repetitive experimental environment, a larger number of images will be required for model training to enable application under more general conditions.
- Open Access
Chloride Diffusion by Build Orientation of Cementitious Material-Based Binder Jetting 3D Printing Mortar
Binder jetting 3D printing (BJ3DP) is used to create geometrical and topology-optimized building structures via architectural geometric design owing to its high degree of freedom in geometry implementation. However, building structures require high mechanical and durability performance. Because of the recent trend of using 3D printing concrete as a structural component in reinforcing bars, its durability with respect to chloride penetration needs to be reviewed. Therefore, in this study, the compressive strength and durability of the chloride diffusion of cement-based 3D-printed output were evaluated. In addition, to confirm the performance difference based on the build orientation, the compressive strength and chloride diffusion were evaluated with respect to the build direction and transverse direction. The experimental results show that the compressive strength was approximately 22.1–26.5% lower in the transverse direction than in the build direction and that the chloride diffusion coefficient was approximately 186.1–407.1% higher in the transverse direction. Consequently, when a structure that requires long-term durability is produced using BJ3DP, it is necessary to examine the design and manufacturing methods in relation to the build orientation in advance.
Open AccessChloride Diffusion by Build Orientation of Cementitious Material-Based Binder Jetting 3D Printing Mortar
Binder jetting 3D printing (BJ3DP) is used to create geometrical and topology-optimized building structures via architectural geometric design owing to its high degree of freedom in geometry implementation. However, building structures require high mechanical and durability performance. Because of the recent trend of using 3D printing concrete as a structural component in reinforcing bars, its durability with respect to chloride penetration needs to be reviewed. Therefore, in this study, the compressive strength and durability of the chloride diffusion of cement-based 3D-printed output were evaluated. In addition, to confirm the performance difference based on the build orientation, the compressive strength and chloride diffusion were evaluated with respect to the build direction and transverse direction. The experimental results show that the compressive strength was approximately 22.1–26.5% lower in the transverse direction than in the build direction and that the chloride diffusion coefficient was approximately 186.1–407.1% higher in the transverse direction. Consequently, when a structure that requires long-term durability is produced using BJ3DP, it is necessary to examine the design and manufacturing methods in relation to the build orientation in advance.