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.

As a case study on aspect ratio behavior, Kaolin, zeolite, TiO2, pozzolan and diatomaceous earth minerals are investigated using wet milling with 0.3 pai media. The grinding process using small media of 0.3 pai is suitable for current work processing applications. Primary particles with average particle size distribution D50, ~6 μm are shifted to submicron size, D50 ~0.6 μm, after grinding. Grinding of particles is characterized by various size parameters such as sphericity as geometric shape, equivalent diameter, and average particle size distribution. Herein, we systematically provide an overview of factors affecting the primary particle size reduction. Energy consumption for grinding is determined using classical grinding laws, including Rittinger's and Kick's laws. Submicron size is obtained at maximum frictional shear stress. Alterations in properties of wettability, heat resistance, thermal conductivity, and adhesion increase with increasing particle surface area. In the comparison of the aspect ratio of the submicron powder, the air heat conductivity and the total heat release amount increase 68 % and 2 times, respectively.

스카른 Zn-Pb-Cu 복합광석을 구성하는 주요 구성 광물의 정량분석을 목적으로, 마이크로 포커스 X-ray 단층촬영 장비를 이용한 스카른 복합광석의 3차원 비파괴검사를 수행하였다. X-ray 단층화상의 화상결함을 감소시키고자 제안된 화상보정법을 이용하여 화상들을 보정한 후에 3차원으로 재구성하였다. 주사전자현미경(SEM)에 의한 표면분석과 보정된 X-ray 단층화상을 비교하여 주요광물에 대한 CT 값의 범위를 결정하였다. 재구성화상 내 전체 광물의 체적비율을 분석한 결과, 황화광물 20.5%, 맥석광물 79.5%로 평가되었다. X-ray 3차원 단층화상 정량분석법은 광석 내 유용광물의 부존형상과 회수율 분석에 유용하게 적용될 것으로 기대된다.