Defect detection and monitoring in metal additive manufactured parts through deep learning of spatially resolved acoustic spectroscopy signals

Jacob Williams, Paul Dryburgh, Adam Clare, Prahalada Rao, Ashok Samal

Research output: Contribution to journalArticle

Abstract

Laser powder bed fusion (LPBF) is an additive manufacturing (AM) process that promises to herald a new age in manufacturing by removing many of the design and material-related constraints of traditional subtractive and formative manufacturing processes. However, the level and severity of defects observed in parts produced by the current class of LPBF systems will not be tolerated in safety-critical applications. Hence, there is a need to introduce information-rich process monitoring to assess part integrity simultaneously with fabrication so that opportune corrective action can be taken to minimize part defects. Spatially Resolved Acoustic Spectroscopy (SRAS) is a uniquely positioned nondestructive acoustic microscopy sensing approach that has been successfully used to probe the mechanical properties and assess the presence of defects in LPBF parts. However, the technique is sensitive to extraneous phenomena, such as surface reflectivity, which occur within the LPBF system and may occlude identification of surface breaking and subsurface defects. With a view to applying the SRAS technique for in-process monitoring in a production-scale LPBF environment and to overcome the foregoing challenge, this study proposes the use of a deep learning convolutional neural network that is termed Densely connected Convolutional Block Architecture for Multimodal Image Regression (DCB-MIR), which invokes SRAS-derived acoustic velocity maps of the part as input data and translates them to an output resembling an optical micrograph. Through this approach, we demonstrate that defects, such as porosity and surface imperfections in titanium alloy and nickel alloy specimens made using LPBF, which were not clearly discernable in the as-measured SRAS acoustic map and were obscured by artifacts in the optical image, are accurately identified. To quantify the accuracy of the approach, the cosine similarity between the predicted output images and target optical images was used as the objective function of DCB-MIR. The cosine similarity between the acquired SRAS signatures and the corresponding as-measured optical micrographs of samples typically ranged between -0.15 and 0.15. In contrast, when the optical micrograph-like images derived from DCB-MIR proposed in this work were compared with the optical signatures, the cosine similarity improved in the range of 0.25 to 0.60.

Original languageEnglish (US)
Pages (from-to)204-226
Number of pages23
JournalSmart and Sustainable Manufacturing Systems
Volume2
Issue number1
DOIs
StatePublished - Nov 19 2018

Fingerprint

Acoustic spectroscopy
Fusion reactions
Powders
Defects
Lasers
Monitoring
Metals
Process monitoring
3D printers
Nickel alloys
Acoustic wave velocity
Titanium alloys
Defect detection
Deep learning
Porosity
Acoustics
Neural networks
Fabrication
Mechanical properties

Keywords

  • Additive manufacturing
  • Deep learning
  • Defect detection
  • Neural networks
  • Process monitoring
  • Spatially resolved acoustic spectroscopy

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering
  • Control and Systems Engineering
  • Computer Science Applications

Cite this

Defect detection and monitoring in metal additive manufactured parts through deep learning of spatially resolved acoustic spectroscopy signals. / Williams, Jacob; Dryburgh, Paul; Clare, Adam; Rao, Prahalada; Samal, Ashok.

In: Smart and Sustainable Manufacturing Systems, Vol. 2, No. 1, 19.11.2018, p. 204-226.

Research output: Contribution to journalArticle

@article{7017a4c925394049923e0ea5ecfb1579,
title = "Defect detection and monitoring in metal additive manufactured parts through deep learning of spatially resolved acoustic spectroscopy signals",
abstract = "Laser powder bed fusion (LPBF) is an additive manufacturing (AM) process that promises to herald a new age in manufacturing by removing many of the design and material-related constraints of traditional subtractive and formative manufacturing processes. However, the level and severity of defects observed in parts produced by the current class of LPBF systems will not be tolerated in safety-critical applications. Hence, there is a need to introduce information-rich process monitoring to assess part integrity simultaneously with fabrication so that opportune corrective action can be taken to minimize part defects. Spatially Resolved Acoustic Spectroscopy (SRAS) is a uniquely positioned nondestructive acoustic microscopy sensing approach that has been successfully used to probe the mechanical properties and assess the presence of defects in LPBF parts. However, the technique is sensitive to extraneous phenomena, such as surface reflectivity, which occur within the LPBF system and may occlude identification of surface breaking and subsurface defects. With a view to applying the SRAS technique for in-process monitoring in a production-scale LPBF environment and to overcome the foregoing challenge, this study proposes the use of a deep learning convolutional neural network that is termed Densely connected Convolutional Block Architecture for Multimodal Image Regression (DCB-MIR), which invokes SRAS-derived acoustic velocity maps of the part as input data and translates them to an output resembling an optical micrograph. Through this approach, we demonstrate that defects, such as porosity and surface imperfections in titanium alloy and nickel alloy specimens made using LPBF, which were not clearly discernable in the as-measured SRAS acoustic map and were obscured by artifacts in the optical image, are accurately identified. To quantify the accuracy of the approach, the cosine similarity between the predicted output images and target optical images was used as the objective function of DCB-MIR. The cosine similarity between the acquired SRAS signatures and the corresponding as-measured optical micrographs of samples typically ranged between -0.15 and 0.15. In contrast, when the optical micrograph-like images derived from DCB-MIR proposed in this work were compared with the optical signatures, the cosine similarity improved in the range of 0.25 to 0.60.",
keywords = "Additive manufacturing, Deep learning, Defect detection, Neural networks, Process monitoring, Spatially resolved acoustic spectroscopy",
author = "Jacob Williams and Paul Dryburgh and Adam Clare and Prahalada Rao and Ashok Samal",
year = "2018",
month = "11",
day = "19",
doi = "10.1520/SSMS20180035",
language = "English (US)",
volume = "2",
pages = "204--226",
journal = "Smart and Sustainable Manufacturing Systems",
issn = "2520-6478",
number = "1",

}

TY - JOUR

T1 - Defect detection and monitoring in metal additive manufactured parts through deep learning of spatially resolved acoustic spectroscopy signals

AU - Williams, Jacob

AU - Dryburgh, Paul

AU - Clare, Adam

AU - Rao, Prahalada

AU - Samal, Ashok

PY - 2018/11/19

Y1 - 2018/11/19

N2 - Laser powder bed fusion (LPBF) is an additive manufacturing (AM) process that promises to herald a new age in manufacturing by removing many of the design and material-related constraints of traditional subtractive and formative manufacturing processes. However, the level and severity of defects observed in parts produced by the current class of LPBF systems will not be tolerated in safety-critical applications. Hence, there is a need to introduce information-rich process monitoring to assess part integrity simultaneously with fabrication so that opportune corrective action can be taken to minimize part defects. Spatially Resolved Acoustic Spectroscopy (SRAS) is a uniquely positioned nondestructive acoustic microscopy sensing approach that has been successfully used to probe the mechanical properties and assess the presence of defects in LPBF parts. However, the technique is sensitive to extraneous phenomena, such as surface reflectivity, which occur within the LPBF system and may occlude identification of surface breaking and subsurface defects. With a view to applying the SRAS technique for in-process monitoring in a production-scale LPBF environment and to overcome the foregoing challenge, this study proposes the use of a deep learning convolutional neural network that is termed Densely connected Convolutional Block Architecture for Multimodal Image Regression (DCB-MIR), which invokes SRAS-derived acoustic velocity maps of the part as input data and translates them to an output resembling an optical micrograph. Through this approach, we demonstrate that defects, such as porosity and surface imperfections in titanium alloy and nickel alloy specimens made using LPBF, which were not clearly discernable in the as-measured SRAS acoustic map and were obscured by artifacts in the optical image, are accurately identified. To quantify the accuracy of the approach, the cosine similarity between the predicted output images and target optical images was used as the objective function of DCB-MIR. The cosine similarity between the acquired SRAS signatures and the corresponding as-measured optical micrographs of samples typically ranged between -0.15 and 0.15. In contrast, when the optical micrograph-like images derived from DCB-MIR proposed in this work were compared with the optical signatures, the cosine similarity improved in the range of 0.25 to 0.60.

AB - Laser powder bed fusion (LPBF) is an additive manufacturing (AM) process that promises to herald a new age in manufacturing by removing many of the design and material-related constraints of traditional subtractive and formative manufacturing processes. However, the level and severity of defects observed in parts produced by the current class of LPBF systems will not be tolerated in safety-critical applications. Hence, there is a need to introduce information-rich process monitoring to assess part integrity simultaneously with fabrication so that opportune corrective action can be taken to minimize part defects. Spatially Resolved Acoustic Spectroscopy (SRAS) is a uniquely positioned nondestructive acoustic microscopy sensing approach that has been successfully used to probe the mechanical properties and assess the presence of defects in LPBF parts. However, the technique is sensitive to extraneous phenomena, such as surface reflectivity, which occur within the LPBF system and may occlude identification of surface breaking and subsurface defects. With a view to applying the SRAS technique for in-process monitoring in a production-scale LPBF environment and to overcome the foregoing challenge, this study proposes the use of a deep learning convolutional neural network that is termed Densely connected Convolutional Block Architecture for Multimodal Image Regression (DCB-MIR), which invokes SRAS-derived acoustic velocity maps of the part as input data and translates them to an output resembling an optical micrograph. Through this approach, we demonstrate that defects, such as porosity and surface imperfections in titanium alloy and nickel alloy specimens made using LPBF, which were not clearly discernable in the as-measured SRAS acoustic map and were obscured by artifacts in the optical image, are accurately identified. To quantify the accuracy of the approach, the cosine similarity between the predicted output images and target optical images was used as the objective function of DCB-MIR. The cosine similarity between the acquired SRAS signatures and the corresponding as-measured optical micrographs of samples typically ranged between -0.15 and 0.15. In contrast, when the optical micrograph-like images derived from DCB-MIR proposed in this work were compared with the optical signatures, the cosine similarity improved in the range of 0.25 to 0.60.

KW - Additive manufacturing

KW - Deep learning

KW - Defect detection

KW - Neural networks

KW - Process monitoring

KW - Spatially resolved acoustic spectroscopy

UR - http://www.scopus.com/inward/record.url?scp=85074051435&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074051435&partnerID=8YFLogxK

U2 - 10.1520/SSMS20180035

DO - 10.1520/SSMS20180035

M3 - Article

AN - SCOPUS:85074051435

VL - 2

SP - 204

EP - 226

JO - Smart and Sustainable Manufacturing Systems

JF - Smart and Sustainable Manufacturing Systems

SN - 2520-6478

IS - 1

ER -