Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Deep Convolutional Neural Networks as a Rapid Screening Tool for Complex Additively Manufactured Structures

Journal Article · · Additive Manufacturing
 [1];  [1];  [1];  [1];  [2];  [1]
  1. Sandia National Lab. (SNL-NM), Albuquerque, NM (United States). Materials, Physical, and Chemical Science Center
  2. Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)

Additively manufactured metamaterials such as lattices offer unique physical properties such as high specific strengths and stiffnesses. However, additively manufactured parts, including lattices, exhibit a higher variability in their mechanical properties than wrought materials, placing more stringent demands on inspection, part quality verification, and product qualification. Previous research on anomaly detection has primarily focused on using in-situ monitoring of the additive manufacturing process or post-process (ex-situ) x-ray computed tomography. In this work, we show that convolutional neural networks (CNN), a machine learning algorithm, can directly predict the energy required to compressively deform gyroid and octet truss metamaterials using only optical images. Using the tiled nature of engineered lattices, the relatively small data set (43 to 48 lattices) can be augmented by systematically subdividing the original image into many smaller sub-images. Furthermore, during testing of the CNN, the prediction from these sub-images can be combined using an ensemble-like technique to predict the deformation work of the entire lattice. This approach provides a fast and inexpensive screening tool for predicting properties of 3D printed lattices. Importantly, this artificial intelligence strategy goes beyond ‘inspection’, since it accurately estimates product performance metrics, not just the existence of defects.

Research Organization:
Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
Sponsoring Organization:
USDOE National Nuclear Security Administration (NNSA)
Grant/Contract Number:
AC04-94AL85000; NA0003525
OSTI ID:
1639094
Alternate ID(s):
OSTI ID: 1809810
Report Number(s):
SAND--2020-7001J; 687224
Journal Information:
Additive Manufacturing, Journal Name: Additive Manufacturing Vol. 35; ISSN 2214-8604
Publisher:
ElsevierCopyright Statement
Country of Publication:
United States
Language:
English

References (27)

Mechanical Metamaterials and Their Engineering Applications journal December 2018
A state-of-the-art review on types, design, optimization, and additive manufacturing of cellular structures journal July 2019
Overview of Materials Qualification Needs for Metal Additive Manufacturing journal January 2016
Energy absorption characteristics of metallic triply periodic minimal surface sheet structures under compressive loading journal October 2018
A multi-scale convolutional neural network for autonomous anomaly detection and classification in a laser powder bed fusion additive manufacturing process journal December 2018
Optimizing Micro-Tiles in Micro-Structures as a Design Paradigm journal October 2019
Parametric design of graded truss lattice structures for enhanced thermal dissipation journal October 2019
MLCPM: A process monitoring framework for 3D metal printing in industrial scale journal October 2018
Design for Additive Manufacturing: Trends, opportunities, considerations, and constraints journal January 2016
Machine learning in tolerancing for additive manufacturing journal January 2018
Machine learning-based image processing for on-line defect recognition in additive manufacturing journal January 2019
Prediction of compressive and flexural strengths of a modified zeolite additive mortar using artificial neural network journal October 2018
High-throughput stochastic tensile performance of additively manufactured stainless steel journal March 2017
Review of in-situ process monitoring and in-situ metrology for metal additive manufacturing journal April 2016
Mechanical properties and energy absorption capability of functionally graded F2BCC lattice fabricated by SLM journal April 2018
Additive manufacturing: scientific and technological challenges, market uptake and opportunities journal January 2018
A cybermanufacturing and AI framework for laser powder bed fusion (LPBF) additive manufacturing process journal August 2019
Surface texture metrology for metal additive manufacturing: a review journal October 2016
Automated Process Monitoring in 3D Printing Using Supervised Machine Learning journal January 2018
Additive manufacturing: Toward holistic design journal July 2017
A comparison of normalization methods for high density oligonucleotide array data based on variance and bias journal January 2003
Lattice Metamaterials with Mechanically Tunable Poisson’s Ratio for Vibration Control journal February 2017
Deep Learning for In Situ and Real-Time Quality Monitoring in Additive Manufacturing Using Acoustic Emission journal September 2019
Strong, lightweight, and recoverable three-dimensional ceramic nanolattices journal September 2014
Metal Additive Manufacturing: A Review of Mechanical Properties journal July 2016
Impact behavior of negative stiffness honeycomb materials journal February 2018
A Round Robin Study for Laser beam Melting in Metal Powder bed journal August 2016

Similar Records

Evolution of global and local deformation in additively manufactured octet truss lattice structures
Journal Article · Thu Oct 21 00:00:00 EDT 2021 · Additive Manufacturing Letters · OSTI ID:1830537