Premium
Identifying build orientation of 3D ‐printed materials using convolutional neural networks
Author(s) -
Strube Jan,
Schram Malachi,
Rustam Sabiha,
Kennedy Zachary,
Varga Tamas
Publication year - 2021
Publication title -
statistical analysis and data mining: the asa data science journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.381
H-Index - 33
eISSN - 1932-1872
pISSN - 1932-1864
DOI - 10.1002/sam.11497
Subject(s) - convolutional neural network , computer science , orientation (vector space) , residual neural network , artificial neural network , architecture , artificial intelligence , ultimate tensile strength , extension (predicate logic) , pattern recognition (psychology) , machine learning , materials science , mathematics , composite material , geometry , art , visual arts , programming language
The advent of additive manufacturing (AM) processes brought with it intense research into various materials and manufacturing processes. At the same time, the need for validation of material properties, as well as study and forecasting of aging, has arisen. Modern imaging techniques, like X‐ray computed tomography (XCT), are a convenient vehicle for such studies; however, the large datasets they produce require novel analysis techniques to efficiently extract critical information. In this paper, we present our work on developing a 3D extension of the ResNet architecture to distinguish between two build orientations of tensile bars produced by AM. Using only information from XCT, our method achieves a 99.3% correct classification at a misidentification of 1%.