skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Identifying build orientation of 3D-printed materials using convolutional neural networks

Abstract

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. Here, 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%.

Authors:
ORCiD logo [1]; ORCiD logo [2];  [3]; ORCiD logo [2]; ORCiD logo [2]
  1. Pacific Northwest National Lab. (PNNL), Richland, WA (United States); Univ. of Oregon, Eugene, OR (United States)
  2. Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
  3. Univ. of Washington, Seattle, WA (United States)
Publication Date:
Research Org.:
Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
Sponsoring Org.:
USDOE Laboratory Directed Research and Development (LDRD) Program; National Science Foundation (NSF)
OSTI Identifier:
1834047
Report Number(s):
PNNL-SA-153051
Journal ID: ISSN 1932-1864
Grant/Contract Number:  
AC05-76RL01830; DGE-1633216
Resource Type:
Journal Article: Accepted Manuscript
Journal Name:
Statistical Analysis and Data Mining
Additional Journal Information:
Journal Volume: 14; Journal Issue: 6; Journal ID: ISSN 1932-1864
Publisher:
Wiley
Country of Publication:
United States
Language:
English
Subject:
36 MATERIALS SCIENCE; deep learning; additive manufacturing

Citation Formats

Strube, Jan F., Schram, Malachi, Rustam, Sabiha, Kennedy, Zachary C., and Varga, Tamas. Identifying build orientation of 3D-printed materials using convolutional neural networks. United States: N. p., 2021. Web. doi:10.1002/sam.11497.
Strube, Jan F., Schram, Malachi, Rustam, Sabiha, Kennedy, Zachary C., & Varga, Tamas. Identifying build orientation of 3D-printed materials using convolutional neural networks. United States. https://doi.org/10.1002/sam.11497
Strube, Jan F., Schram, Malachi, Rustam, Sabiha, Kennedy, Zachary C., and Varga, Tamas. 2021. "Identifying build orientation of 3D-printed materials using convolutional neural networks". United States. https://doi.org/10.1002/sam.11497. https://www.osti.gov/servlets/purl/1834047.
@article{osti_1834047,
title = {Identifying build orientation of 3D-printed materials using convolutional neural networks},
author = {Strube, Jan F. and Schram, Malachi and Rustam, Sabiha and Kennedy, Zachary C. and Varga, Tamas},
abstractNote = {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. Here, 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%.},
doi = {10.1002/sam.11497},
url = {https://www.osti.gov/biblio/1834047}, journal = {Statistical Analysis and Data Mining},
issn = {1932-1864},
number = 6,
volume = 14,
place = {United States},
year = {Thu Jan 07 00:00:00 EST 2021},
month = {Thu Jan 07 00:00:00 EST 2021}
}

Works referenced in this record:

VoxNet: A 3D Convolutional Neural Network for real-time object recognition
conference, September 2015


Deep Residual Learning for Image Recognition
conference, June 2016


An image evaluation approach for parameter-based product form and color design
journal, February 2006


Classifying the Dimensional Variation in Additive Manufactured Parts From Laser-Scanned Three-Dimensional Point Cloud Data Using Machine Learning Approaches
journal, June 2017


Data-driven cost estimation for additive manufacturing in cybermanufacturing
journal, January 2018


Gradient-based learning applied to document recognition
journal, January 1998


A Convolutional Neural Network Model for Predicting a Product's Function, Given Its Form
journal, October 2017