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.

Abstract
1. 서 론
2. 실험 방법
3. 결과 및 고찰
    3.1. 공정 변수와 조형체 밀도, 기공의 형상과의 상관
    3.2. 기공 형상 분류를 위한 기계 학습 적용
4. 결 론
References

• 김은아(한국재료연구원 3D프린팅재료연구실/부산대학교 재료공학과) | Eun-Ah Kim (3D printing materials research center, Korea Institute of Materials Science/Materials Science and Engineering, Pusan national university)
• 권세훈(부산대학교 재료공학과) | Se-Hun Kwon (Materials Science and Engineering, Pusan national university)
• 양동열(한국재료연구원 3D프린팅재료연구실) | Dong-Yeol Yang (3D printing materials research center, Korea Institute of Materials Science)
• 유지훈(한국재료연구원 3D프린팅재료연구실) | Ji-Hun Yu (3D printing materials research center, Korea Institute of Materials Science)
• 김권일(C51) | Kwon-Ill Kim
• 이학성(한국재료연구원 3D프린팅재료연구실) | Hak-Sung Lee (3D printing materials research center, Korea Institute of Materials Science) Corresponding Author