Characterization of nanoscale precipitates in superalloy 718 using high resolution SEM imaging

Smith, Timothy M.; Senanayake, Nishan M.; Sudbrack, Chantal K.; Bonacuse, Peter J.; Rogers, Richard B.; Chao, Paul; Carter, Jennifer L. W.

doi:10.1016/j.matchar.2018.12.018

Cited by 28 publications

(15 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SEM micrographs in IN718Net were acquired at the NASA Glenn Research Center and the representative sample preparation and imaging conditions are presented in T.M. Smith et al [16]. The dataset consists of 47 unique 900 × 900 px micrographs acquired from additively manufactured IN718 samples.…”

Section: In718net Datasetmentioning

confidence: 99%

“…Since this is not a machine learning approach, it does not require a labeled "ground truth" training dataset. The five major algorithm steps are described briefly below and the detailed explanation and the results are presented in Smith et al [16].…”

Section: Mathematical Image Processing (Non-machine Learning Approach)mentioning

confidence: 99%

“…We recently implemented an image processing method using mathematical algorithms (non-machine learning) which achieves up to 94% accuracy compared to ground truth as determined by manual segmentation [16]. The approach was based on finding the edge points, assigning symmetrical points to the edge points in a given radius, and the classical ellipse fitting to estimate the missing part of the contours.…”

Section: Introductionmentioning

confidence: 99%

“…In this work, we have compared the previously validated mathematical algorithm [16] with traditional (RF and SVM) and novel (CNN with U-Net architecture) machine learning approaches to segment the composite particles in SEM images of IN718. The different methods of computing-containerizing and possible usage of GPUs have been applied to each of the approaches in order to compare the resource allocation and the time effectiveness.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Computer Vision Approaches for Segmentation of Nanoscale Precipitates in Nickel-Based Superalloy IN718

Senanayake

Carter

2020

Integr Mater Manuf Innov

View full text Add to dashboard Cite

Extracting accurate volume fraction and size measurements of γ″ and γ′ precipitates in iron-based superalloys from micrographs is challenging and conventionally involves manual image processing due to their smaller size, and similar crystal structures and chemistries. The co-precipitation of composite particles further complicates automated segmentation. In this work, different types of traditional machine learning approaches and a convolutional neural network (CNN) were compared to a non-machine learning approach, for the segmentation of the composite particles of γ″ and γ′ precipitates. The objective was to optimize metrics of segmentation accuracy and the required computational resources. The data set contains 47 experimentally generated scanning electron micrographs of IN718 alloy samples, computationally increased to 188 images (900 × 900 px). All algorithms are containerized using singularity, publicly available, and can be modified without dependencies. The CNN and the random forest models achieve 95% and 94% accuracy, respectively, on the test images with better computational efficiency than the non-machine learning algorithm. The CNN tested accurately over a range of imaging conditions.

show abstract

Section: In718net Datasetmentioning

confidence: 99%

Section: Mathematical Image Processing (Non-machine Learning Approach)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Computer Vision Approaches for Segmentation of Nanoscale Precipitates in Nickel-Based Superalloy IN718

Senanayake

Carter

2020

Integr Mater Manuf Innov

View full text Add to dashboard Cite

show abstract

“…I gave two talks at EUROMAT focused on the application of data science to integrate novel approaches to explore for quantifying nanoscale precipitates in superalloy 718 3 The TMS Foundation has given promising young scientists and engineers a chance to develop important scientific collaborations across global cultures since 2006 through the TMS Young Leaders International Scholar program. In cooperation with the Japan Institute of Metals and Materials (JIM) and the Federation of European Materials Societies (FEMS), the TMS Foundation has enabled early career professionals, selected by a competitive review of their accomplishments, to travel to the JIM and FEMS annual meetings to present scientific papers and participate in learning and networking activities.…”

mentioning

confidence: 99%

Gaining a Global Perspective at EUROMAT 2019 A TMS/FEMS International Scholar Report

2019

JOM

View full text Add to dashboard Cite

How Can the Non-metallic Inclusion Distributions Lead to an Anisotropy in the Fatigue Life Durability of Forged γ/γ′ Ni-Based Disks Alloys?

Govaere,

Al Kotob,

Baudequin

et al. 2024

The Minerals, Metals &Amp; Materials Series

View full text Add to dashboard Cite

Characterization of nanoscale precipitates in superalloy 718 using high resolution SEM imaging

Cited by 28 publications

References 22 publications

Computer Vision Approaches for Segmentation of Nanoscale Precipitates in Nickel-Based Superalloy IN718

Computer Vision Approaches for Segmentation of Nanoscale Precipitates in Nickel-Based Superalloy IN718

Gaining a Global Perspective at EUROMAT 2019 A TMS/FEMS International Scholar Report

How Can the Non-metallic Inclusion Distributions Lead to an Anisotropy in the Fatigue Life Durability of Forged γ/γ′ Ni-Based Disks Alloys?

Contact Info

Product

Resources

About