Reducing lack of fusion voids in 3D printing using machine learning скачать в хорошем качестве

Reducing lack of fusion voids in 3D printing using machine learning

00:00 Introduction 01:56 Lack of fusion defects 02:35 Why is machine learning needed? 03:40 Our novel approach 05:10 Ranking of important variables 06:12 Lack of fusion index 07:07 Process maps 08:16 Main contributions Lack of fusion defects in 3D printed parts affect the mechanical properties and may lead to part rejection. They are currently reduced by expensive post-processing such as hot isostatic pressing or by time-consuming experimental trial-and-error. We combine a large volume of reliable historical data, human intelligence derived from the rich knowledge base of metallurgy and physics-based models, and machine learning. We provide a verifiable quantitative index for achieving fully dense superior parts, facilitate material selection, uncover the hierarchy of important variables that affect the density, and present easy-to-use visual process maps. These findings can improve the quality consistency of 3D printed parts that now limit their greater industrial adaptation. More details are available in the following paper: M. Jiang, T Mukherjee, Y. Du, T DebRoy, Superior printed parts using history and augmented machine learning, npj Computational Materials, 2022, vol. 8, Article number: 184. Available at: https://www.nature.com/articles/s4152... #additivemanufacturing #3dprinting #machinelearning #voids #modeling #physics #defects #data #dataanalytics