https://orcid.org/0000-0003-4432-3920
Abstract
Laser powder bed fusion (LPBF) is a popular additive manufacturing process with many advantages compared with traditional (subtractive) manufacturing. However, ensuring the quality of LPBF parts remains a challenge in the manufacturing industry. This work proposes the use of unsupervised learning, specifically, the k-means clustering method, to identify unique melt pool shapes produced during LPBF manufacturing. Melt pools are a key process signature in LPBF and can assist in the evaluation of process quality. k-means is employed multiple times sequentially to produce clusters of melt pools, and the silhouette value is used to identify the optimal number of clusters. The clusters produced by k-means are used as labels to train a deep neural network to classify the melt pool shapes. By inputting the melt pool image and the corresponding LPBF machine process parameters into the neural network, the neural network identifies the melt pool shape to aid human analysis and provide insight into part quality. The trained neural network is interpreted using explainable artificial intelligence (XAI) methods to investigate the relationships between process parameters and the melt pool shape. Using layer-wise relevance propagation, the process parameters that most significantly influence the melt pool shapes are identified. The relationship between process parameters and melt pool shapes can be useful for selecting the process parameters to produce the desired melt pool shapes. In summary, this study describes an approach that combines unsupervised machine learning and XAI methods to effectively enable the analysis and interpretation of melt pools.
Issue Section:
Technical Papers
References
1.
Chowdhury
S.
, Yadaiah
N.
, Prakash
C.
, Ramakrishna
S.
, Dixit
S.
, Gupta
L. R.
, and Buddhi
D.
, “Laser Powder Bed Fusion: A State-of-the-Art Review of the Technology, Materials, Properties & Defects, and Numerical Modelling
,” Journal of Materials Research and Technology
20
(2022
): 2109
–2172
, https://doi.org/10.1016/j.jmrt.2022.07.1212.
Tofail
S. A. M.
, Koumoulos
E. P.
, Bandyopadhyay
A.
, Bose
S.
, O’Donoghue
L.
, and Charitidis
C.
, “Additive Manufacturing: Scientific and Technological Challenges, Market Uptake and Opportunities
,” Materials Today
21
, no. 1
(January–February 2018
): 22
–37
, https://doi.org/10.1016/j.mattod.2017.07.0013.
King
W. E.
, Anderson
A. T.
, Ferencz
R. M.
, Hodge
N. E.
, Kamath
C.
, Khairallah
S. A.
, and Rubenchik
A. M.
, “Laser Powder Bed Fusion Additive Manufacturing of Metals; Physics, Computational, and Materials Challenges
,” Applied Physics Reviews
2
, no. 4
(December 2015
): 041304, https://doi.org/10.1063/1.49378094.
Du
C.
, Zhao
Y.
, Jiang
J.
, Wang
Q.
, Wang
H.
, Li
N.
, and Sun
J.
, “Pore Defects in Laser Powder Bed Fusion: Formation Mechanism, Control Method, and Perspectives
,” Journal of Alloys and Compounds
944
(2023
): 169215, https://doi.org/10.1016/j.jallcom.2023.1692155.
Chia
H. Y.
, Wu
J.
, Wang
X.
, and Yan
W.
, “Process Parameter Optimization of Metal Additive Manufacturing: A Review and Outlook
,” Journal of Materials Informatics
2
, no. 4
(October 2022
): 16, https://doi.org/10.20517/jmi.2022.186.
Wang
J.
, Zhu
R.
, Liu
Y.
, and Zhang
L.
, “Understanding Melt Pool Characteristics in Laser Powder Bed Fusion: An Overview of Single- and Multi-track Melt Pools for Process Optimization
,” Advanced Powder Materials
2
, no. 4
(October 2023
): 100137, https://doi.org/10.1016/j.apmate.2023.1001377.
Thompson
A.
, Maskery
I.
, and Leach
R. K.
, “X-ray Computed Tomography for Additive Manufacturing: A Review
,” Measurement Science and Technology
27
, no. 7
(July 2016
): 072001, https://doi.org/10.1088/0957-0233/27/7/0720018.
Kim
C.
, Yin
H.
, Shmatok
A.
, Prorok
B. C.
, Lou
X.
, and Matlack
K. H.
, “Ultrasonic Nondestructive Evaluation of Laser Powder Bed Fusion 316L Stainless Steel
,” Additive Manufacturing
38
(2021
): 101800, https://doi.org/10.1016/j.addma.2020.1018009.
McCann
R.
, Obeidi
M. A.
, Hughes
C.
, McCarthy
É.
, Egan
D. S.
, Vijayaraghavan
R. K.
, Joshi
A. M.
, et al., “In-Situ Sensing, Process Monitoring and Machine Control in Laser Powder Bed Fusion: A Review
,” Additive Manufacturing
45
(2021
): 102058, https://doi.org/10.1016/j.addma.2021.10205810.
Drissi-Daoudi
R.
, Masinelli
G.
, de Formanoir
C.
, Wasmer
K.
, Jhabvala
J.
, and Logé
R. E.
, “Acoustic Emission for the Prediction of Processing Regimes in Laser Powder Bed Fusion, and the Generation of Processing Maps
,” Additive Manufacturing
67
(2023
): 103484, https://doi.org/10.1016/j.addma.2023.10348411.
Gordon
J. V.
, Narra
S. P.
, Cunningham
R. W.
, Liu
H.
, Chen
H.
, Suter
R. M.
, Beuth
J. L.
, and Rollett
A. D.
, “Defect Structure Process Maps for Laser Powder Bed Fusion Additive Manufacturing
,” Additive Manufacturing
36
(2020
): 101552, https://doi.org/10.1016/j.addma.2020.10155212.
Tang
M.
, Pistorius
P. C.
, and Beuth
J. L.
, “Prediction of Lack-of-Fusion Porosity for Powder Bed Fusion
,” Additive Manufacturing
14
(2017
): 39
–48
, https://doi.org/10.1016/j.addma.2016.12.00113.
Olleak
A.
and Xi
Z.
, “Efficient LPBF Process Simulation Using Finite Element Modeling with Adaptive Remeshing for Distortions and Residual Stresses Prediction
,” Manufacturing Letters
24
(2020
): 140
–144
, https://doi.org/10.1016/j.mfglet.2020.05.00214.
Bayat
M.
, Mohanty
S.
, and Hattel
J. H.
, “Multiphysics Modelling of Lack-of-Fusion Voids Formation and Evolution in IN718 Made by Multi-track/Multi-layer L-PBF
,” International Journal of Heat and Mass Transfer
139
(2019
): 95
–114
, https://doi.org/10.1016/j.ijheatmasstransfer.2019.05.00315.
Wong
V. W. H.
, Ferguson
M.
, Law
K. H.
, Lee
Y.-T. T.
, and Witherell
P.
, “Segmentation of Additive Manufacturing Defects Using U-Net
,” Journal of Computing and Information Science in Engineering
22
, no. 3
(June 2022
): 031005, https://doi.org/10.1115/1.405307816.
Ansari
M. A.
, Crampton
A.
, Garrard
R.
, Cai
B.
, and Attallah
M.
, “A Convolutional Neural Network (CNN) Classification to Identify the Presence of Pores in Powder Bed Fusion Images
,” International Journal of Advanced Manufacturing Technology
120
, no. 7
(June 2022
): 5133
–5150
, https://doi.org/10.1007/s00170-022-08995-717.
Zhang
Y.
, Shapiro
V.
, and Witherell
P.
, “A Neighborhood-Based Neural Network for Melt Pool Prediction and Control
,” in ASME 2020 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference
(New York: American Society of Mechanical Engineers
, 2020
), V009T09A026, https://doi.org/10.1115/DETC2020-2254918.
Akbari
P.
, Ogoke
F.
, Kao
N.-Y.
, Meidani
K.
, Yeh
C.-Y.
, Lee
W.
, and Barati Farimani
A.
. “MeltpoolNet: Melt Pool Characteristic Prediction in Metal Additive Manufacturing Using Machine Learning
,” Additive Manufacturing
55
(2022
): 102817, https://doi.org/10.1016/j.addma.2022.10281719.
Fathizadan
S.
, Ju
F.
, and Lu
Y.
, “Deep Representation Learning for Process Variation Management in Laser Powder Bed Fusion
,” Additive Manufacturing
42
(2021
): 101961, https://doi.org/10.1016/j.addma.2021.10196120.
Scime
L.
and Beuth
J.
, “Using Machine Learning to Identify In-Situ Melt Pool Signatures Indicative of Flaw Formation in a Laser Powder Bed Fusion Additive Manufacturing Process
,” Additive Manufacturing
25
(2019
): 151
–165
, https://doi.org/10.1016/j.addma.2018.11.01021.
Sato
M. M.
, Wong
V. W. H.
, Law
K. H.
, Yeung
H.
, Yang
Z.
, Lane
B.
, and Witherell
P.
, “Anomaly Detection of Laser Powder Bed Fusion Melt Pool Images Using Combined Unsupervised and Supervised Learning Methods
,” in ASME 2022 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference
(New York
: American Society of Mechanical Engineers
, 2022
), V002T02A070, https://doi.org/10.1115/DETC2022-8831322.
Simonyan
K.
, Vedaldi
A.
, and Zisserman
A.
, “Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
” (paper presentation, Second International Conference on Learning Representations, Alberta, CA, April 14–16, 2014
), https://doi.org/10.48550/arXiv.1312.603423.
Selvaraju
R. R.
, Cogswell
M.
, Das
A.
, Vedantam
R.
, Parikh
D.
, and Batra
D.
, “Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
,” International Journal of Computer Vision
128
, no. 2
(February 2020
): 336
–359
, https://doi.org/10.1007/s11263-019-01228-724.
Lundberg
S.
and Lee
S.-I.
, “A Unified Approach to Interpreting Model Predictions
,” in NIPS’17: Proceedings of the 31st International Conference on Neural Information Processing Systems
, ed. von Luxburg
U.
, Guyon
I.
, Bengio
S.
, Wallach
H.
, and Fergus
R.
(Red Hook, NY
: Curran Associates
, 2017
), 4768
–4777
.25.
Ribeiro
M.
, Singh
S.
, and Guestrin
C.
, “‘Why Should I Trust You?’: Explaining the Predictions of Any Classifier
,” in 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations
(Kerrville, TX
: Association for Computational Linguistics
, 2016
), 97
–101
, https://doi.org/10.18653/v1/N16-302026.
Lee
J. A.
, Sagong
M. J.
, Jung
J.
, Kim
E. S.
, and Kim
H. S.
, “Explainable Machine Learning for Understanding and Predicting Geometry and Defect Types in Fe-Ni Alloys Fabricated by Laser Metal Deposition Additive Manufacturing
,” Journal of Materials Research and Technology
22
(2023
): 413
–423
, https://doi.org/10.1016/j.jmrt.2022.11.13727.
Pandiyan
V.
, Wróbel
R.
, Leinenbach
C.
, and Shevchik
S.
, “Optimizing In-Situ Monitoring for Laser Powder Bed Fusion Process: Deciphering Acoustic Emission and Sensor Sensitivity with Explainable Machine Learning
,” Journal of Materials Processing Technology
321
(2023
): 118144, https://doi.org/10.1016/j.jmatprotec.2023.11814428.
Pratap
A.
, Sardana
N.
, Utomo
S.
, John
A.
, Karthikeyan
P.
, and Hsiung
P.-A.
, “Analysis of Defect Associated with Powder Bed Fusion with Deep Learning and Explainable AI
,” in 2023 15th International Conference on Knowledge and Smart Technology (KST)
(Piscataway, NJ
: Institute of Electrical and Electronics Engineers
, 2023
), 1
–6
, https://doi.org/10.1109/KST57286.2023.1008690529.
Sato
M. M.
, Wong
V. W. H.
, Law
K. H.
, Yeung
H.
, and Witherell
P.
, “Explainability of Laser Powder Bed Fusion Melt Pool Classification Using Deep Learning
,” in ASME 2023 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference
(New York
: American Society of Mechanical Engineers
, 2023
), V002T02A054, https://doi.org/10.1115/DETC2023-10913730.
Ko
H.
, Witherell
P.
, Lu
Y.
, Kim
S.
, and Rosen
D. W.
, “Machine Learning and Knowledge Graph Based Design Rule Construction for Additive Manufacturing
,” Additive Manufacturing
37
(2021
): 101620, https://doi.org/10.1016/j.addma.2020.10162031.
Lloyd
S.
, “Least Squares Quantization in PCM
,” IEEE Transactions on Information Theory
28
, no. 2
(March 1982
): 129
–137
, https://doi.org/10.1109/TIT.1982.105648932.
Sculley
D.
, “Web-Scale K-Means Clustering
,” in 19th International Conference on World Wide Web
(New York
: Association for Computing Machinery
, 2010
), 1177
–1178
, https://doi.org/10.1145/1772690.177286233.
Rousseeuw
P. J.
, “Silhouettes: A Graphical Aid to the Interpretation and Validation of Cluster Analysis
,” Journal of Computational and Applied Mathematics
20
(1987
): 53
–65
, https://doi.org/10.1016/0377-0427(87)90125-734.
Xiong
H.
, Wu
J.
, and Chen
J.
, “K-Means Clustering Versus Validation Measures: A Data-Distribution Perspective
,” IEEE Transactions on Systems, Man, and Cybernetics. Part B, (Cybernetics)
39
, no. 2
(April 2009
): 318
–331
, https://doi.org/10.1109/TSMCB.2008.200455935.
Liang
J.
, Bai
L.
, Dang
C.
, and Cao
F.
, “The K-Means-Type Algorithms Versus Imbalanced Data Distributions
,” IEEE Transactions on Fuzzy Systems
20
, no. 4
(August 2012
): 728
–745
, https://doi.org/10.1109/TFUZZ.2011.218235436.
van der Maaten
L.
and Hinton
G.
, “Visualizing Data Using T-SNE
,” Journal of Machine Learning Research
9
, no. 86
(November 2008
): 2579
–2605
.37.
Scime
L.
and Beuth
J.
, “A Multi-scale Convolutional Neural Network for Autonomous Anomaly Detection and Classification in a Laser Powder Bed Fusion Additive Manufacturing Process
,” Additive Manufacturing
24
(2018
): 273
–286
, https://doi.org/10.1016/j.addma.2018.09.03438.
Zhang
B.
, Liu
S.
, and Shin
Y. C.
. “In-Process Monitoring of Porosity during Laser Additive Manufacturing Process
,” Additive Manufacturing
28
(2019
): 497
–505
, https://doi.org/10.1016/j.addma.2019.05.03039.
Bach
S.
, Binder
A.
, Montavon
G.
, Klauschen
F.
, Müller
K.-R.
, and Samek
W.
, “On Pixel-Wise Explanations for Non-linear Classifier Decisions by Layer-Wise Relevance Propagation
,” PLoS One
10
, no. 7
(July 2015
): e0130140, https://doi.org/10.1371/journal.pone.013014040.
Montavon
G.
, Binder
A.
, Lapuschkin
S.
, Samek
W.
, and Müller
K.-R.
, “Layer-Wise Relevance Propagation: An Overview
,” in Explainable AI: Interpreting, Explaining and Visualizing Deep Learning
, ed. Samek
W.
, Montavon
G.
, Vedaldi
A.
, Hansen
L. K.
, and Müller
K.-R.
(Cham, Switzerland
: Springer Cham
, 2019
), 193
–209
, https://doi.org/10.1007/978-3-030-28954-6_1041.
Lane
B. M.
, Mekhontsev
S.
, Grantham
S. E.
, Vlasea
M.
, Whiting
J. G.
, Yeung
H.
, Fox
J. C.
, et al., “Design, Developments, and Results from the NIST Additive Manufacturing Metrology Testbed (AMMT)
,” in Solid Freeform Fabrication Symposium
(Gaithersburg, MD
: National Institute of Standards and Technology
, 2016
), 1145
–1160
.42.
Lane
B.
and Yeung
H.
, “Process Monitoring Dataset from the Additive Manufacturing Metrology Testbed (AMMT): ‘Three-Dimensional Scan Strategies,’
” Journal of Research of the National Institute of Standards and Technology
124
, no. 124033
(November 2019
): 1
–14
, https://doi.org/10.6028/jres.124.03343.
Lane
B.
and Yeung
H.
, “Process Monitoring Dataset from the Additive Manufacturing Metrology Testbed (AMMT): 3D Scan Strategies
,” NIST, 2019
, http://web.archive.org/web/20240226205814/https://data.nist.gov/pdr/lps/85196AB9232E7202E053245706813DFA204444.
Yeung
H.
and Lane
B.
, “A Residual Heat Compensation Based Scan Strategy for Powder Bed Fusion Additive Manufacturing
,” Manufacturing Letters
25
(August 2020
): 56
–59
, https://doi.org/10.1016/j.mfglet.2020.07.00545.
He
K.
, Zhang
X.
, Ren
S.
, and Sun
J.
, “Deep Residual Learning for Image Recognition
,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
(Piscataway, NJ
: Institute of Electrical and Electronics Engineers
, 2016
), 770
–778
, https://doi.org/10.1109/CVPR.2016.9046.
Deng
J.
, Dong
W.
, Socher
R.
, Li
L.-J.
, Li
K.
, and Fei-Fei
L.
, “ImageNet: A Large-Scale Hierarchical Image Database
,” in 2009 IEEE Conference on Computer Vision and Pattern Recognition
(Piscataway, NJ
: Institute of Electrical and Electronics Engineers
, 2009
), 248
–255
, https://doi.org/10.1109/CVPR.2009.520684847.
Glorot
X.
and Bengio
Y.
, “Understanding the Difficulty of Training Deep Feedforward Neural Networks
,” The Journal of Machine Learning Research
9
(2010
): 249
–256
.48.
Kingma
D. P.
and Ba
J.
, “Adam: A Method for Stochastic Optimization
” (paper presentation, Third International Conference on Learning Representations, San Diego, CA, May 7–9, 2015
).
This content is only available via PDF.
All rights reserved. This material may not be reproduced or copied, in whole or part, in any printed, mechanical, electronic, film, or other distribution and storage media, without the written consent of ASTM International.
You do not currently have access to this content.
