Deep Learning Based Automatic Porosity Detection of Laser Powder Bed Fusion Additive Manufacturing

Syed Ibn Mohsin; Behzad Farhang; Peng Wang; Yiran Yang; Narges Shayesteh; Fazleena Badurdeen

doi:10.1007/978-3-031-38241-3_37

Deep Learning Based Automatic Porosity Detection of Laser Powder Bed Fusion Additive Manufacturing

Syed Ibn Mohsin, Behzad Farhang, Peng Wang, Yiran Yang, Narges Shayesteh, Fazleena Badurdeen

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

Laser Powder Bed Fusion (LPBF) is a widely utilized additive manufacturing process. Despite its popularity, LPBF has been found to have limitations in terms of the reliability and repeatability of its parts. To address these limitations, a deep learning model based on You Only Look Once (YOLO) was adapted to automate the detection of defect areas from scanning electron microscopic images of LPBF-manufactured parts. The data on the defect areas are then integrated into an Artificial Neural Network to correlate the process parameters with defects. The results show that the development of defects is stochastic in nature with respect to the input process parameters. The high variability of defects generated from the same process parameters makes it difficult to reliably predict the quality of the parts using only a process data-driven approach. This highlights the importance of in-situ monitoring of the system for reliable prediction of part quality.

Original language	English
Title of host publication	Flexible Automation and Intelligent Manufacturing
Subtitle of host publication	Establishing Bridges for More Sustainable Manufacturing Systems - Proceedings of FAIM 2023
Editors	Francisco J. G. Silva, Raul D.S.G. Campilho, António B. Pereira
Pages	328-335
Number of pages	8
DOIs	https://doi.org/10.1007/978-3-031-38241-3_37
State	Published - 2024
Event	32nd International Conference on Flexible Automation and Intelligent Manufacturing, FAIM 2023 - Porto, Portugal Duration: Jun 18 2023 → Jun 22 2023

Publication series

Name	Lecture Notes in Mechanical Engineering
ISSN (Print)	2195-4356
ISSN (Electronic)	2195-4364

Conference

Conference	32nd International Conference on Flexible Automation and Intelligent Manufacturing, FAIM 2023
Country/Territory	Portugal
City	Porto
Period	6/18/23 → 6/22/23

Bibliographical note

Publisher Copyright:
© 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Keywords

Additive Manufacturing
Machine Learning
Powder Bed Fusion

ASJC Scopus subject areas

Automotive Engineering
Aerospace Engineering
Mechanical Engineering
Fluid Flow and Transfer Processes

Access to Document

10.1007/978-3-031-38241-3_37

Cite this

Mohsin, S. I., Farhang, B., Wang, P., Yang, Y., Shayesteh, N., & Badurdeen, F. (2024). Deep Learning Based Automatic Porosity Detection of Laser Powder Bed Fusion Additive Manufacturing. In F. J. G. Silva, R. D. S. G. Campilho, & A. B. Pereira (Eds.), Flexible Automation and Intelligent Manufacturing: Establishing Bridges for More Sustainable Manufacturing Systems - Proceedings of FAIM 2023 (pp. 328-335). (Lecture Notes in Mechanical Engineering). https://doi.org/10.1007/978-3-031-38241-3_37

Mohsin, Syed Ibn ; Farhang, Behzad ; Wang, Peng et al. / Deep Learning Based Automatic Porosity Detection of Laser Powder Bed Fusion Additive Manufacturing. Flexible Automation and Intelligent Manufacturing: Establishing Bridges for More Sustainable Manufacturing Systems - Proceedings of FAIM 2023. editor / Francisco J. G. Silva ; Raul D.S.G. Campilho ; António B. Pereira. 2024. pp. 328-335 (Lecture Notes in Mechanical Engineering).

@inproceedings{90828799a6d84e3f8d576d9f4c24479b,

title = "Deep Learning Based Automatic Porosity Detection of Laser Powder Bed Fusion Additive Manufacturing",

abstract = "Laser Powder Bed Fusion (LPBF) is a widely utilized additive manufacturing process. Despite its popularity, LPBF has been found to have limitations in terms of the reliability and repeatability of its parts. To address these limitations, a deep learning model based on You Only Look Once (YOLO) was adapted to automate the detection of defect areas from scanning electron microscopic images of LPBF-manufactured parts. The data on the defect areas are then integrated into an Artificial Neural Network to correlate the process parameters with defects. The results show that the development of defects is stochastic in nature with respect to the input process parameters. The high variability of defects generated from the same process parameters makes it difficult to reliably predict the quality of the parts using only a process data-driven approach. This highlights the importance of in-situ monitoring of the system for reliable prediction of part quality.",

keywords = "Additive Manufacturing, Machine Learning, Powder Bed Fusion",

author = "Mohsin, {Syed Ibn} and Behzad Farhang and Peng Wang and Yiran Yang and Narges Shayesteh and Fazleena Badurdeen",

note = "Publisher Copyright: {\textcopyright} 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 32nd International Conference on Flexible Automation and Intelligent Manufacturing, FAIM 2023 ; Conference date: 18-06-2023 Through 22-06-2023",

year = "2024",

doi = "10.1007/978-3-031-38241-3_37",

language = "English",

isbn = "9783031382406",

series = "Lecture Notes in Mechanical Engineering",

pages = "328--335",

editor = "Silva, {Francisco J. G.} and Campilho, {Raul D.S.G.} and Pereira, {Ant{\'o}nio B.}",

booktitle = "Flexible Automation and Intelligent Manufacturing",

}

Mohsin, SI, Farhang, B, Wang, P, Yang, Y, Shayesteh, N & Badurdeen, F 2024, Deep Learning Based Automatic Porosity Detection of Laser Powder Bed Fusion Additive Manufacturing. in FJG Silva, RDSG Campilho & AB Pereira (eds), Flexible Automation and Intelligent Manufacturing: Establishing Bridges for More Sustainable Manufacturing Systems - Proceedings of FAIM 2023. Lecture Notes in Mechanical Engineering, pp. 328-335, 32nd International Conference on Flexible Automation and Intelligent Manufacturing, FAIM 2023, Porto, Portugal, 6/18/23. https://doi.org/10.1007/978-3-031-38241-3_37

Deep Learning Based Automatic Porosity Detection of Laser Powder Bed Fusion Additive Manufacturing. / Mohsin, Syed Ibn; Farhang, Behzad; Wang, Peng et al.
Flexible Automation and Intelligent Manufacturing: Establishing Bridges for More Sustainable Manufacturing Systems - Proceedings of FAIM 2023. ed. / Francisco J. G. Silva; Raul D.S.G. Campilho; António B. Pereira. 2024. p. 328-335 (Lecture Notes in Mechanical Engineering).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Deep Learning Based Automatic Porosity Detection of Laser Powder Bed Fusion Additive Manufacturing

AU - Mohsin, Syed Ibn

AU - Farhang, Behzad

AU - Wang, Peng

AU - Yang, Yiran

AU - Shayesteh, Narges

AU - Badurdeen, Fazleena

PY - 2024

Y1 - 2024

N2 - Laser Powder Bed Fusion (LPBF) is a widely utilized additive manufacturing process. Despite its popularity, LPBF has been found to have limitations in terms of the reliability and repeatability of its parts. To address these limitations, a deep learning model based on You Only Look Once (YOLO) was adapted to automate the detection of defect areas from scanning electron microscopic images of LPBF-manufactured parts. The data on the defect areas are then integrated into an Artificial Neural Network to correlate the process parameters with defects. The results show that the development of defects is stochastic in nature with respect to the input process parameters. The high variability of defects generated from the same process parameters makes it difficult to reliably predict the quality of the parts using only a process data-driven approach. This highlights the importance of in-situ monitoring of the system for reliable prediction of part quality.

AB - Laser Powder Bed Fusion (LPBF) is a widely utilized additive manufacturing process. Despite its popularity, LPBF has been found to have limitations in terms of the reliability and repeatability of its parts. To address these limitations, a deep learning model based on You Only Look Once (YOLO) was adapted to automate the detection of defect areas from scanning electron microscopic images of LPBF-manufactured parts. The data on the defect areas are then integrated into an Artificial Neural Network to correlate the process parameters with defects. The results show that the development of defects is stochastic in nature with respect to the input process parameters. The high variability of defects generated from the same process parameters makes it difficult to reliably predict the quality of the parts using only a process data-driven approach. This highlights the importance of in-situ monitoring of the system for reliable prediction of part quality.

KW - Additive Manufacturing

KW - Machine Learning

KW - Powder Bed Fusion

UR - http://www.scopus.com/inward/record.url?scp=85171571881&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85171571881&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-38241-3_37

DO - 10.1007/978-3-031-38241-3_37

M3 - Conference contribution

AN - SCOPUS:85171571881

SN - 9783031382406

T3 - Lecture Notes in Mechanical Engineering

SP - 328

EP - 335

BT - Flexible Automation and Intelligent Manufacturing

A2 - Silva, Francisco J. G.

A2 - Campilho, Raul D.S.G.

A2 - Pereira, António B.

T2 - 32nd International Conference on Flexible Automation and Intelligent Manufacturing, FAIM 2023

Y2 - 18 June 2023 through 22 June 2023

ER -

Mohsin SI, Farhang B, Wang P, Yang Y, Shayesteh N, Badurdeen F. Deep Learning Based Automatic Porosity Detection of Laser Powder Bed Fusion Additive Manufacturing. In Silva FJG, Campilho RDSG, Pereira AB, editors, Flexible Automation and Intelligent Manufacturing: Establishing Bridges for More Sustainable Manufacturing Systems - Proceedings of FAIM 2023. 2024. p. 328-335. (Lecture Notes in Mechanical Engineering). doi: 10.1007/978-3-031-38241-3_37

Deep Learning Based Automatic Porosity Detection of Laser Powder Bed Fusion Additive Manufacturing

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this