Heterogeneous sensor-based condition monitoring in directed energy deposition

Mohammad Montazeri, Abdalla R. Nassar, Christopher B. Stutzman, Prahalada Rao

Research output: Contribution to journalArticle

Abstract

The objective of this work is to detect in situ the occurrence of lack-of-fusion defects in titanium alloy (Ti-6Al-4 V) parts made using directed energy deposition (DED) additive manufacturing (AM). We use data from two types of in-process sensors, namely, a spectrometer and an optical camera which are integrated into an Optomec MR-7 DED machine. Both sensors are focused on capturing the dynamic phenomena around the melt pool region. To detect lack-of-fusion defects, we fuse (combine) the data from the in-process sensors invoking the concept of Kronecker product of graphs. Subsequently, we use the features derived from the graph Kronecker product as inputs to a machine learning algorithm to predict the severity (class or level) of average length of lack-of-fusion defects within a layer, which is obtained from offline X-ray computed tomography of the test parts. We demonstrate that the severity of lack-of-fusion defects is classified with statistical fidelity (F-score) close to 85% for a two-level classification scenario, and approximately 70% for a three-level classification scenario. Accordingly, this work demonstrates the use of heterogeneous in-process sensing and online data analytics for in situ detection of defects in DED metal AM process.

Original languageEnglish (US)
Article number100916
JournalAdditive Manufacturing
Volume30
DOIs
StatePublished - Dec 2019

Fingerprint

Condition monitoring
3D printers
Fusion reactions
Defects
Sensors
Electric fuses
Titanium alloys
Learning algorithms
Tomography
Learning systems
Spectrometers
Metals
Cameras
X rays

All Science Journal Classification (ASJC) codes

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

Cite this

Montazeri, Mohammad ; Nassar, Abdalla R. ; Stutzman, Christopher B. ; Rao, Prahalada. / Heterogeneous sensor-based condition monitoring in directed energy deposition. In: Additive Manufacturing. 2019 ; Vol. 30.
@article{f4b9db47f1dd4a52a7d51d53b9eb978c,
title = "Heterogeneous sensor-based condition monitoring in directed energy deposition",
abstract = "The objective of this work is to detect in situ the occurrence of lack-of-fusion defects in titanium alloy (Ti-6Al-4 V) parts made using directed energy deposition (DED) additive manufacturing (AM). We use data from two types of in-process sensors, namely, a spectrometer and an optical camera which are integrated into an Optomec MR-7 DED machine. Both sensors are focused on capturing the dynamic phenomena around the melt pool region. To detect lack-of-fusion defects, we fuse (combine) the data from the in-process sensors invoking the concept of Kronecker product of graphs. Subsequently, we use the features derived from the graph Kronecker product as inputs to a machine learning algorithm to predict the severity (class or level) of average length of lack-of-fusion defects within a layer, which is obtained from offline X-ray computed tomography of the test parts. We demonstrate that the severity of lack-of-fusion defects is classified with statistical fidelity (F-score) close to 85{\%} for a two-level classification scenario, and approximately 70{\%} for a three-level classification scenario. Accordingly, this work demonstrates the use of heterogeneous in-process sensing and online data analytics for in situ detection of defects in DED metal AM process.",
author = "Mohammad Montazeri and Nassar, {Abdalla R.} and Stutzman, {Christopher B.} and Prahalada Rao",
year = "2019",
month = "12",
doi = "10.1016/j.addma.2019.100916",
language = "English (US)",
volume = "30",
journal = "Additive Manufacturing",
issn = "2214-8604",
publisher = "Elsevier BV",

}

Heterogeneous sensor-based condition monitoring in directed energy deposition. / Montazeri, Mohammad; Nassar, Abdalla R.; Stutzman, Christopher B.; Rao, Prahalada.

In: Additive Manufacturing, Vol. 30, 100916, 12.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Heterogeneous sensor-based condition monitoring in directed energy deposition

AU - Montazeri, Mohammad

AU - Nassar, Abdalla R.

AU - Stutzman, Christopher B.

AU - Rao, Prahalada

PY - 2019/12

Y1 - 2019/12

N2 - The objective of this work is to detect in situ the occurrence of lack-of-fusion defects in titanium alloy (Ti-6Al-4 V) parts made using directed energy deposition (DED) additive manufacturing (AM). We use data from two types of in-process sensors, namely, a spectrometer and an optical camera which are integrated into an Optomec MR-7 DED machine. Both sensors are focused on capturing the dynamic phenomena around the melt pool region. To detect lack-of-fusion defects, we fuse (combine) the data from the in-process sensors invoking the concept of Kronecker product of graphs. Subsequently, we use the features derived from the graph Kronecker product as inputs to a machine learning algorithm to predict the severity (class or level) of average length of lack-of-fusion defects within a layer, which is obtained from offline X-ray computed tomography of the test parts. We demonstrate that the severity of lack-of-fusion defects is classified with statistical fidelity (F-score) close to 85% for a two-level classification scenario, and approximately 70% for a three-level classification scenario. Accordingly, this work demonstrates the use of heterogeneous in-process sensing and online data analytics for in situ detection of defects in DED metal AM process.

AB - The objective of this work is to detect in situ the occurrence of lack-of-fusion defects in titanium alloy (Ti-6Al-4 V) parts made using directed energy deposition (DED) additive manufacturing (AM). We use data from two types of in-process sensors, namely, a spectrometer and an optical camera which are integrated into an Optomec MR-7 DED machine. Both sensors are focused on capturing the dynamic phenomena around the melt pool region. To detect lack-of-fusion defects, we fuse (combine) the data from the in-process sensors invoking the concept of Kronecker product of graphs. Subsequently, we use the features derived from the graph Kronecker product as inputs to a machine learning algorithm to predict the severity (class or level) of average length of lack-of-fusion defects within a layer, which is obtained from offline X-ray computed tomography of the test parts. We demonstrate that the severity of lack-of-fusion defects is classified with statistical fidelity (F-score) close to 85% for a two-level classification scenario, and approximately 70% for a three-level classification scenario. Accordingly, this work demonstrates the use of heterogeneous in-process sensing and online data analytics for in situ detection of defects in DED metal AM process.

UR - http://www.scopus.com/inward/record.url?scp=85074173782&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074173782&partnerID=8YFLogxK

U2 - 10.1016/j.addma.2019.100916

DO - 10.1016/j.addma.2019.100916

M3 - Article

AN - SCOPUS:85074173782

VL - 30

JO - Additive Manufacturing

JF - Additive Manufacturing

SN - 2214-8604

M1 - 100916

ER -