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

Strube, Jan F.; Schram, Malachi; Rustam, Sabiha; Kennedy, Zachary C.; Varga, Tamas

doi:10.1002/sam.11497

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:

^[1];

^[2]; Rustam, Sabiha ^[3];

^[2];

^[2]

Pacific Northwest National Lab. (PNNL), Richland, WA (United States); Univ. of Oregon, Eugene, OR (United States)
Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
Univ. of Washington, Seattle, WA (United States)

Publication Date:: 2021-01-07

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.

Copy to clipboard


                    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

Copy to clipboard


                    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.

Copy to clipboard


                    
@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         = {2021},

  month        = {1}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Accepted Manuscript (DOE)

Publisher's Version of Record

https://doi.org/10.1002/sam.11497

Other availability

Search WorldCat to find libraries that may hold this journal

Save / Share:

Export Metadata

Save to My Library

Works referenced in this record:

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

Maturana, Daniel; Scherer, Sebastian
2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
https://doi.org/10.1109/IROS.2015.7353481

Build orientation dependent microstructure in polymer laser sintering: Relationship to part performance and evolution with aging
journal, December 2020

Battu, Anil K.; Pope, Timothy R.; Varga, Tamas
Additive Manufacturing, Vol. 36
https://doi.org/10.1016/j.addma.2020.101464

Deep Residual Learning for Image Recognition
conference, June 2016

He, Kaiming; Zhang, Xiangyu; Ren, Shaoqing
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
https://doi.org/10.1109/CVPR.2016.90

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

Tsai, Hung-Cheng; Hsiao, Shih-Wen; Hung, Fei-Kung
Computer-Aided Design, Vol. 38, Issue 2
https://doi.org/10.1016/j.cad.2005.10.001

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

Samie Tootooni, M.; Dsouza, Ashley; Donovan, Ryan
Journal of Manufacturing Science and Engineering, Vol. 139, Issue 9
https://doi.org/10.1115/1.4036641

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

Chan, Siu L.; Lu, Yanglong; Wang, Yan
Journal of Manufacturing Systems, Vol. 46
https://doi.org/10.1016/j.jmsy.2017.12.001

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

Lecun, Y.; Bottou, L.; Bengio, Y.
Proceedings of the IEEE, Vol. 86, Issue 11
https://doi.org/10.1109/5.726791

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

Dering, Matthew L.; Tucker, Conrad S.
Journal of Mechanical Design, Vol. 139, Issue 11
https://doi.org/10.1115/1.4037309

Similar records in OSTI.GOV collections:

The Application of Convolutional Neural Networks (CNNs) to Recognize Defects in 3D-Printed Parts

Journal Article Wen, Hao; Huang, Chang; Guo, Shengmin - Materials

Cracks and pores are two common defects in metallic additive manufacturing (AM) parts. In this paper, deep learning-based image analysis is performed for defect (cracks and pores) classification/detection based on SEM images of metallic AM parts. Three different levels of complexities, namely, defect classification, defect detection and defect image segmentation, are successfully achieved using a simple CNN model, the YOLOv4 model and the Detectron2 object detection library, respectively. The tuned CNN model can classify any single defect as either a crack or pore at almost 100% accuracy. The other two models can identify more than 90% of the cracks andmore »« less
https://doi.org/10.3390/ma14102575
Beam Hardening Artifact Reduction in X-Ray CT Reconstruction of 3D Printed Metal Parts Leveraging Deep Learning and CAD Models

Conference Ziabari, Amir; Venkatakrishnan, Singanallur; Kirka, Michael; ...

Nondestructive evaluation (NDE) of additively manufactured (AM) parts is important for understanding the impacts of various process parameters and qualifying the built part. X-ray computed tomography (XCT) has played a critical role in rapid NDE and characterization of AM parts. However, XCT of metal AM parts can be challenging because of artifacts produced by standard reconstruction algorithms as a result of a confounding effect called “beam hardening.” Beam hardening artifacts complicate the analysis of XCT images and adversely impact the process of detecting defects, such as pores and cracks, which is key to ensuring the quality of the parts beingmore »« less
https://doi.org/10.1115/IMECE2020-23766

Full Text Available
Algorithm-Based Fault Tolerance for Convolutional Neural Networks

Journal Article Zhao, Kai; Di, Sheng; Li, Sihuan; ... - IEEE Transactions on Parallel and Distributed Systems

Convolutional neural networks (CNNs) are becoming more and more important for solving challenging and critical problems in many fields. CNN inference applications have been deployed in safety-critical systems, which may suffer from soft errors caused by high-energy particles, high temperature, or abnormal voltage. Of critical importance is ensuring the stability of the CNN inference process against soft errors. Traditional fault tolerance methods are not suitable for CNN inference because error-correcting code is unable to protect computational components, instruction duplication techniques incur high overhead, and existing algorithm-based fault tolerance (ABFT) techniques cannot protect all convolution implementations. In this paper, we focusmore »« less
https://doi.org/10.1109/tpds.2020.3043449

Full Text Available
Simurgh: A Framework for Cad-Driven Deep Learning Based X-Ray CT Reconstruction

Conference Ziabari, Amir; Venkatakrishnan, Singanallur; Dubey, Abhishek; ...

High-resolution X-ray computed tomography (XCT) is an important technique for the inspection of additively manufactured (AM) parts. While XCT is typically used off-line to inspect a subset of manufactured parts, significantly accelerating measurement speed while retaining accuracy would enable use of XCT for in-line inspection to rapidly identify defects in each part as it is manufactured. Here, we propose a deep learning (DL) based approach that uses computer aided design (CAD) models of the AM parts and physics-based information to rapidly produce high-quality reconstructions from sparse XCT measurements without high quality ground truth data. Our approach uses a generative adversarialmore »« less
Full Text Available
Scaling Resolution of Gigapixel Whole Slide Images Using Spatial Decomposition on Convolutional Neural Networks

Conference Tsaris, Aristeidis (aris); Yoon, Hong-Jun; Dash, Sajal; ...

Gigapixel images are prevalent in scientific domains ranging from remote sensing, and satellite imagery to microscopy, etc. However, training a deep learning model at the natural resolution of those images has been a challenge in terms of both, overcoming the resource limit (e.g. HBM memory constraints), as well as scaling up to a large number of GPUs. In this paper, we trained Residual neural Networks (ResNet) on 22,528 x 22,528-pixel size images using a distributed spatial decomposition method on 2,304 GPUs on the Summit Supercomputer. We applied our method on a Whole Slide Imaging (WSI) dataset from The Cancer Genomemore »« less
https://doi.org/10.1145/3592979.3593401

Full Text Available

Similar Records

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

Abstract

Citation Formats

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

Build orientation dependent microstructure in polymer laser sintering: Relationship to part performance and evolution with aging journal, December 2020

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

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

Build orientation dependent microstructure in polymer laser sintering: Relationship to part performance and evolution with aging
journal, December 2020

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