基于深度学习的3D打印球形粉末颗粒自动统计与测量  

Particle auto-statistics and measurement of the spherical powder for 3D printing based on deep learning

作　　者：王祎超 张政[1] 黄海洲[1] 林文雄[1] Wang Yichao;Zhang Zheng;Huang Haizhou;Lin Wenxiong(Fujian Institute of Research on the Structure of Matter,Chinese Academy of Sciences,Fuzhou 350002,China;University of the Chinese Academy of Sciences,Beijing 100049,China)

机构地区：[1]中国科学院福建物质结构研究所,福建福州350002 [2]中国科学院大学,北京100049

出　　处：《红外与激光工程》2021年第10期245-254,共10页Infrared and Laser Engineering

基　　金：中国科学院科技服务网络计划区域重点项目(KFJ-STS-QYZD-2021-10-002)。

摘　　要：随着金属粉末3D打印技术的不断发展,如何从显微图像中准确提取粉末颗粒的粒形粒径和球化率信息变得越来越重要。文中基于深度学习算法Mask R-CNN,提出了一种电镜图像球形粉末颗粒自动统计与测量的方法。该方法可对单幅显微图像上超过1 000个颗粒进行自动识别,有效检测电镜图像中的遮挡颗粒,并且生成粒径分布、球形度和球化率统计结果。相比传统图像分割算法,颗粒识别准确度提升了23.6%。相比激光干涉仪的粒径分布测量结果,文中提出的方法可以将位于较大球形粉末上黏附的小颗粒也有效识别出来。With the development of metal powder 3 D printing technology, how to accurately extract the particle size and spheroidization rate information of powder particles from microscopic images has gained much more importance. In this paper, a particle auto-statistics and measurement system on microscopic imaging of the spherical powder was presented, based on one deep learning framework—Mask R-CNN. The proposed model can efficiently detect more than 1 000 particles in a microscopy image, even under the existence of many occlusion particles, and provide statistical results of particle size distribution, degree of sphericity and spheroidization ratio,simultaneously. Compared with traditional image segmentation method, the particle recognition accuracy was improved by 23.6%. Moreover, smaller particles that stuck on big particles can be recognized, according to the comparison in particle size distribution between proposed method and the laser diffraction technique.

关 键 词：粒径分布 球形度 球化率 深度学习 Mask R-CNN 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]