X-ray tomography 분석과 기계 학습을 활용한 금속 3D 프린팅 소재 내의 기공 형태 분류
Characterization and Classification of Pores in Metal 3D Printing Materials with X-ray Tomography and Machine Learning
- 문서 유형
- 연구출판물 · 학술지 논문
- 등재
- KCI
- 저널 순위
- KCI Q2
- 저널
- 한국분말재료학회지 (KPMI)28(3) · pp.208 · 2021
- 피인용
- KCI 0
- ISSN
- 2799-8525
저자
- 김은아제1저자한국재료연구원
- 권세훈부산대학교
- 양동열한국재료연구원
- 유지훈한국재료연구원
- 김권일C51
- 이학성교신저자한국재료연구원
초록
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.
키워드
Machine LearningAdditive manufacturingMetal 3D printingX-ray tomographyComputer vision
식별자
- KCI
- ART002734521



로그인
연구물 목록으로