Application of supervised machine learning for defect detection during metallic powder bed fusion additive manufacturing using high resolution imaging.

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Process monitoring in additive manufacturing (AM) is a crucial component in the mission of broadening AM industrialization. However, conventional part evaluation and qualification techniques, such as computed tomography (CT), can only be utilized after the build is complete, and thus eliminate any potential to correct defects during the build process. In contrast to post-build CT, in situ defect detection based on in situ sensing, such as layerwise visual inspection, enables the potential for in-process re-melting and correction of detected defects and thus facilitates in-process part qualification. This paper describes the development and implementation of such an in situ defect detection strategy for powder bed fusion (PBF) AM using supervised machine learning. During the build process, multiple images were collected at each build layer using a high resolution digital single-lens reflex (DSLR) camera. For each neighborhood in the resulting layerwise image stack, multi-dimensional visual features were extracted and evaluated using binary classification techniques, i.e. a linear support vector machine (SVM). Through binary classification, neighborhoods are then categorized as either a flaw, i.e. an undesirable interruption in the typical structure of the material, or a nominal build condition. Ground truth labels, i.e. the true location of flaws and nominal build areas, which are needed to train the binary classifiers, were obtained from post-build high-resolution 3D CT scan data. In CT scans, discontinuities, e.g. incomplete fusion, porosity, cracks, or inclusions, were identified using automated analysis tools or manual inspection. The xyz locations of the CT data were transferred into the layerwise image domain using an affine transformation, which was estimated using reference points embedded in the part. After the classifier had been properly trained, in situ defect detection accuracies greater than 80% were demonstrated during cross-validation experiments.

Original languageEnglish (US)
Pages (from-to)517-528
Number of pages12
JournalAdditive Manufacturing
Volume21
DOIs
StatePublished - May 1 2018

Fingerprint

3D printers
Powders
Tomography
Learning systems
Fusion reactions
Imaging techniques
Defects
Classifiers
Inspection
Camera lenses
Process monitoring
Support vector machines
Labels
Melting
Porosity
Defect detection
Cracks

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering
  • Materials Science(all)
  • Engineering (miscellaneous)
  • Industrial and Manufacturing Engineering

Cite this

@article{7c33959f7070403a97e08c18662895bb,
title = "Application of supervised machine learning for defect detection during metallic powder bed fusion additive manufacturing using high resolution imaging.",
abstract = "Process monitoring in additive manufacturing (AM) is a crucial component in the mission of broadening AM industrialization. However, conventional part evaluation and qualification techniques, such as computed tomography (CT), can only be utilized after the build is complete, and thus eliminate any potential to correct defects during the build process. In contrast to post-build CT, in situ defect detection based on in situ sensing, such as layerwise visual inspection, enables the potential for in-process re-melting and correction of detected defects and thus facilitates in-process part qualification. This paper describes the development and implementation of such an in situ defect detection strategy for powder bed fusion (PBF) AM using supervised machine learning. During the build process, multiple images were collected at each build layer using a high resolution digital single-lens reflex (DSLR) camera. For each neighborhood in the resulting layerwise image stack, multi-dimensional visual features were extracted and evaluated using binary classification techniques, i.e. a linear support vector machine (SVM). Through binary classification, neighborhoods are then categorized as either a flaw, i.e. an undesirable interruption in the typical structure of the material, or a nominal build condition. Ground truth labels, i.e. the true location of flaws and nominal build areas, which are needed to train the binary classifiers, were obtained from post-build high-resolution 3D CT scan data. In CT scans, discontinuities, e.g. incomplete fusion, porosity, cracks, or inclusions, were identified using automated analysis tools or manual inspection. The xyz locations of the CT data were transferred into the layerwise image domain using an affine transformation, which was estimated using reference points embedded in the part. After the classifier had been properly trained, in situ defect detection accuracies greater than 80{\%} were demonstrated during cross-validation experiments.",
author = "Christian Gobert and Reutzel, {Edward William} and Jan Petrich and Nassar, {Abdalla Ramadan} and Shashi Phoha",
year = "2018",
month = "5",
day = "1",
doi = "10.1016/j.addma.2018.04.005",
language = "English (US)",
volume = "21",
pages = "517--528",
journal = "Additive Manufacturing",
issn = "2214-8604",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - Application of supervised machine learning for defect detection during metallic powder bed fusion additive manufacturing using high resolution imaging.

AU - Gobert, Christian

AU - Reutzel, Edward William

AU - Petrich, Jan

AU - Nassar, Abdalla Ramadan

AU - Phoha, Shashi

PY - 2018/5/1

Y1 - 2018/5/1

N2 - Process monitoring in additive manufacturing (AM) is a crucial component in the mission of broadening AM industrialization. However, conventional part evaluation and qualification techniques, such as computed tomography (CT), can only be utilized after the build is complete, and thus eliminate any potential to correct defects during the build process. In contrast to post-build CT, in situ defect detection based on in situ sensing, such as layerwise visual inspection, enables the potential for in-process re-melting and correction of detected defects and thus facilitates in-process part qualification. This paper describes the development and implementation of such an in situ defect detection strategy for powder bed fusion (PBF) AM using supervised machine learning. During the build process, multiple images were collected at each build layer using a high resolution digital single-lens reflex (DSLR) camera. For each neighborhood in the resulting layerwise image stack, multi-dimensional visual features were extracted and evaluated using binary classification techniques, i.e. a linear support vector machine (SVM). Through binary classification, neighborhoods are then categorized as either a flaw, i.e. an undesirable interruption in the typical structure of the material, or a nominal build condition. Ground truth labels, i.e. the true location of flaws and nominal build areas, which are needed to train the binary classifiers, were obtained from post-build high-resolution 3D CT scan data. In CT scans, discontinuities, e.g. incomplete fusion, porosity, cracks, or inclusions, were identified using automated analysis tools or manual inspection. The xyz locations of the CT data were transferred into the layerwise image domain using an affine transformation, which was estimated using reference points embedded in the part. After the classifier had been properly trained, in situ defect detection accuracies greater than 80% were demonstrated during cross-validation experiments.

AB - Process monitoring in additive manufacturing (AM) is a crucial component in the mission of broadening AM industrialization. However, conventional part evaluation and qualification techniques, such as computed tomography (CT), can only be utilized after the build is complete, and thus eliminate any potential to correct defects during the build process. In contrast to post-build CT, in situ defect detection based on in situ sensing, such as layerwise visual inspection, enables the potential for in-process re-melting and correction of detected defects and thus facilitates in-process part qualification. This paper describes the development and implementation of such an in situ defect detection strategy for powder bed fusion (PBF) AM using supervised machine learning. During the build process, multiple images were collected at each build layer using a high resolution digital single-lens reflex (DSLR) camera. For each neighborhood in the resulting layerwise image stack, multi-dimensional visual features were extracted and evaluated using binary classification techniques, i.e. a linear support vector machine (SVM). Through binary classification, neighborhoods are then categorized as either a flaw, i.e. an undesirable interruption in the typical structure of the material, or a nominal build condition. Ground truth labels, i.e. the true location of flaws and nominal build areas, which are needed to train the binary classifiers, were obtained from post-build high-resolution 3D CT scan data. In CT scans, discontinuities, e.g. incomplete fusion, porosity, cracks, or inclusions, were identified using automated analysis tools or manual inspection. The xyz locations of the CT data were transferred into the layerwise image domain using an affine transformation, which was estimated using reference points embedded in the part. After the classifier had been properly trained, in situ defect detection accuracies greater than 80% were demonstrated during cross-validation experiments.

UR - http://www.scopus.com/inward/record.url?scp=85045293094&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045293094&partnerID=8YFLogxK

U2 - 10.1016/j.addma.2018.04.005

DO - 10.1016/j.addma.2018.04.005

M3 - Article

VL - 21

SP - 517

EP - 528

JO - Additive Manufacturing

JF - Additive Manufacturing

SN - 2214-8604

ER -