ADVANCED-STEM-BASED DEEP LEARNING FOR SEMANTIC SEGMENTATION OF DEFECTS IN STEELS

Title: ADVANCED-STEM-BASED DEEP LEARNING FOR SEMANTIC SEGMENTATION OF DEFECTS IN STEELS

Full Record
Other Related Research

Abstract

In this work, we developed a novel deep convolutional neural network (DCNN) model, called DefectNet, for robust and automated semantic segmentation of three crystallographic defects including line dislocations, precipitates and voids commonly observed in structural metals and alloys. In previous work, we established an experimental protocol for a diffraction contrast imaging scanning transmission electron microscopy (DCI STEM) technique and tailored it specifically for imaging defects in popular iron-based structural alloy. Thus, the DefectNet was trained over a small but high-quality DCI STEM defect image sets of a HT-9 martensitic steel before and after neutron irradiation for 111.8 dpa at 412°C. For the defect quantification that typically takes at least half an hour even for an expert, with a good model the machine learning algorithm can produce more reproducible and reliable quantification in a few seconds. This work demonstrates the feasibility of using deep learning algorithms for fast and accurate defect quantitative analysis.

Authors:

Zhu, Yuanyuan ^[1]; Roberts, Graham W. ^[2]; Sainju, Rajat ^[1]; Hutchinson, Brian J. ^[3];

^[2]; Toloczko, Mychailo B. ^[2]; Edwards, Danny J. ^[2];

^[2]

University of Connecticut
BATTELLE (PACIFIC NW LAB)
WESTERN WASHINGTON UNIVERSITY

Publication Date:: 2019-03-29

Research Org.:: Pacific Northwest National Lab. (PNNL), Richland, WA (United States)

Sponsoring Org.:: USDOE

OSTI Identifier:: 1569022

Report Number(s):: PNNL-SA-141280

DOE Contract Number:: AC05-76RL01830

Resource Type:: Book

Country of Publication:: United States

Language:: English

Subject:: Machine Learning, Radiation effects, Image analysis, semantic segmentation

Citation Formats


                    Zhu, Yuanyuan, Roberts, Graham W., Sainju, Rajat, Hutchinson, Brian J., Kurtz, Richard J., Toloczko, Mychailo B., Edwards, Danny J., and Henager, Charles H. ADVANCED-STEM-BASED DEEP LEARNING FOR SEMANTIC SEGMENTATION OF DEFECTS IN STEELS.  United States: N. p., 2019. 
        Web.

Copy to clipboard


                    Zhu, Yuanyuan, Roberts, Graham W., Sainju, Rajat, Hutchinson, Brian J., Kurtz, Richard J., Toloczko, Mychailo B., Edwards, Danny J., & Henager, Charles H. ADVANCED-STEM-BASED DEEP LEARNING FOR SEMANTIC SEGMENTATION OF DEFECTS IN STEELS.  United States.

Copy to clipboard


                    Zhu, Yuanyuan, Roberts, Graham W., Sainju, Rajat, Hutchinson, Brian J., Kurtz, Richard J., Toloczko, Mychailo B., Edwards, Danny J., and Henager, Charles H. Fri .  
        "ADVANCED-STEM-BASED DEEP LEARNING FOR SEMANTIC SEGMENTATION OF DEFECTS IN STEELS".  United States.

Copy to clipboard


                    
@article{osti_1569022,

  title        = {ADVANCED-STEM-BASED DEEP LEARNING FOR SEMANTIC SEGMENTATION OF DEFECTS IN STEELS},

  author       = {Zhu, Yuanyuan and Roberts, Graham W. and Sainju, Rajat and Hutchinson, Brian J. and Kurtz, Richard J. and Toloczko, Mychailo B. and Edwards, Danny J. and Henager, Charles H.},

  abstractNote = {In this work, we developed a novel deep convolutional neural network (DCNN) model, called DefectNet, for robust and automated semantic segmentation of three crystallographic defects including line dislocations, precipitates and voids commonly observed in structural metals and alloys. In previous work, we established an experimental protocol for a diffraction contrast imaging scanning transmission electron microscopy (DCI STEM) technique and tailored it specifically for imaging defects in popular iron-based structural alloy. Thus, the DefectNet was trained over a small but high-quality DCI STEM defect image sets of a HT-9 martensitic steel before and after neutron irradiation for 111.8 dpa at 412°C. For the defect quantification that typically takes at least half an hour even for an expert, with a good model the machine learning algorithm can produce more reproducible and reliable quantification in a few seconds. This work demonstrates the feasibility of using deep learning algorithms for fast and accurate defect quantitative analysis.},

  doi          = {},

  url          = {https://www.osti.gov/biblio/1569022},
  journal      = {},
number       = ,

  volume       = ,

  place        = {United States},

  year         = {2019},

  month        = {3}

}

Copy to clipboard

Book:

Other availability

Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this book.

Save / Share:

Export Metadata

Save to My Library

Similar records in OSTI.GOV collections:

Deep Learning for Semantic Segmentation of Defects in Advanced STEM Images of Steels

Journal Article Roberts, Graham ; Haile, Simon ; Sainju, Rajat ; ... - Scientific Reports

Crystalline materials exhibit long-range ordered lattice unit, within which resides nonperiodic structural features called defects. These crystallographic defects play a vital role in determining the physical and mechanical properties of a wide range of material systems. While computer vision has demonstrated success in recognizing feature patterns in images with well defined contrast, automated identification of nanometer scale crystallographic defects in electron micrographs governed by complex contrast mechanism is still a challenging task. Here, building upon an advanced defect imaging mode that offers high feature clarity, we introduce DefectSegNet - a new convolutional neural network (CNN) architecture that performs semantic segmentationmore »« less
https://doi.org/10.1038/s41598-019-49105-0

Full Text Available
Towards bend-contour-free dislocation imaging via diffraction contrast STEM

Journal Article Zhu, Yuanyuan ; Ophus, Colin ; Toloczko, Mychailo B. ; ... - Ultramicroscopy

Dislocation imaging using transmission electron microscopy (TEM) has been an invaluable tool for characterizing crystallographic defects in metals. Compared to conventional TEM imaging, diffraction contrast imaging scanning transmission electron microscopy (DCI STEM) with appropriate setting can provide better defect contrast with almost negligible bend contour artifacts, enabling more effective analysis of dislocation structures. Here, we investigated why STEM can suppresses bend contour, and how dislocation contrast behaves along with different STEM imaging parameters. Using a body-centered cubic HT-9 ferritic/martensitic alloy as an example, a simple procedure and operational theory are described at the beginning to help set up DCI STEMmore »« less
Cited by 6
https://doi.org/10.1016/j.ultramic.2018.06.001

Full Text Available
Layer-wise anomaly detection and classification for powder bed additive manufacturing processes: A machine-agnostic algorithm for real-time pixel-wise semantic segmentation

Journal Article Scime, Luke ; Siddel, Derek ; Baird, Seth ; ... - Additive Manufacturing

Increasing industry acceptance of powder bed metal Additive Manufacturing requires improved real-time detection and classification of anomalies. Many of these anomalies, such as recoater blade impacts, binder deposition issues, spatter generation, and some porosities, are surface-visible at each layer of the building process. In this work, the authors present a novel Convolutional Neural Network architecture for pixel-wise localization (semantic segmentation) of layer-wise powder bed imaging data. Key advantages of the algorithm include its ability to return segmentation results at the native resolution of the imaging sensor, seamlessly transfer learned knowledge between different Additive Manufacturing machines, and provide real-time performance. Themore »« less
https://doi.org/10.1016/j.addma.2020.101453
Automated correlative segmentation of large Transmission X-ray Microscopy (TXM) tomograms using deep learning

Journal Article Shashank Kaira, C. ; Yang, Xiaogang ; De Andrade, Vincent ; ... - Materials Characterization

Highlights: • A unique automated segmentation approach for large 3D nanotomography datasets obtained by Transmission X-ray Microscopy (TXM) in an Al-Cu alloy. • Automated segmentation using a Convolutional Neural Network (CNN) architecture based on a deep learning approach was employed. • This extremely versatile technique is capable of emulating the manual segmentation process effectively. • Quantitative comparison between manual segmentation and CNN architecture established the accuracy of this automated technique. • Its ability to robustly process ultra-large volumes of data in relatively small time frames can exponentially accelerate tomographic data analysis. - Abstract: A unique correlative approach for automated segmentationmore »« less
https://doi.org/10.1016/J.MATCHAR.2018.05.053
Understanding important features of deep learning models for segmentation of high-resolution transmission electron microscopy images

Journal Article Horwath, James P. ; Zakharov, Dmitri N. ; Mégret, Rémi ; ... - npj Computational Materials

Cutting edge deep learning techniques allow for image segmentation with great speed and accuracy. However, application to problems in materials science is often difficult since these complex models may have difficultly learning meaningful image features that would enable extension to new datasets. In situ electron microscopy provides a clear platform for utilizing automated image analysis. In this work, we consider the case of studying coarsening dynamics in supported nanoparticles, which is important for understanding, for example, the degradation of industrial catalysts. By systematically studying dataset preparation, neural network architecture, and accuracy evaluation, we describe important considerations in applying deep learningmore »« less
https://doi.org/10.1038/s41524-020-00363-x

Full Text Available

Similar Records