Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jun 27, 2026

Real-Time Imaging of Bonding in 3D-Printed Layers
04:36

Real-Time Imaging of Bonding in 3D-Printed Layers

Published on: September 1, 2023

Machine Learning-Enabled Layer-Wise Melting Quality Recognition for Laser Powder Bed Fusion Process via In Situ

Yuan Liu1, Bowei Zou2, Zhizhou Zhang1,3

  • 1School of Mechanics and Construction Engineering, Jinan University, Guangzhou 510632, China.

Materials (Basel, Switzerland)
|June 26, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

[Application of near infrared spectroscopy technique based on support vector machine in the measurement of moisture and protein contents in Surimi].

Guang pu xue yu guang pu fen xi = Guang pu·2012
Same author

[Effect of TGRJ on blood press, NO and Ang II in renal hypertensive rats].

Zhong yao cai = Zhongyaocai = Journal of Chinese medicinal materials·2012
Same author

Algal genomes reveal evolutionary mosaicism and the fate of nucleomorphs.

Nature·2012
Same author

CD47 deficiency does not impede polymorphonuclear neutrophil transmigration but attenuates granulopoiesis at the postacute stage of colitis.

Journal of immunology (Baltimore, Md. : 1950)·2012
Same author

Network motifs in the transcriptional regulation network of cervical carcinoma cells respond to EGF.

Archives of gynecology and obstetrics·2012
Same author

Theoretical investigation of the proton transfer mechanism in guanine-cytosine and adenine-thymine base pairs.

The Journal of chemical physics·2012
Same journal

Correction: Yang et al. Microstructural Characteristics of High-Pressure Die Casting with High Strength-Ductility Synergy Properties: A Review. <i>Materials</i> 2023, <i>16</i>, 1954.

Materials (Basel, Switzerland)·2026
Same journal

Effect of La and Ce Microalloying on the Corrosion Resistance of 0.4Sb Low-Alloy Steel in a Harsh Marine Atmospheric Environment.

Materials (Basel, Switzerland)·2026
Same journal

High-Temperature Properties of Magnesium Ammonium Phosphate Cement Modified with Gold Tailings.

Materials (Basel, Switzerland)·2026
Same journal

A Study on the Evolution of Intermetallic Phase Microstructure and High-Temperature Creep Behavior in Mg-8.0Al-1.0Nd-1.5Gd-Mn Alloys.

Materials (Basel, Switzerland)·2026
Same journal

Material-Driven Clinical Complications in Mechanical Circulatory Support: From Blood-Material Interactions to Device-Related Adverse Events.

Materials (Basel, Switzerland)·2026
Same journal

Influence of Final Irrigation on Calcium Silicate-Based Sealer Dentinal Tubular Penetration: A Systematic Review.

Materials (Basel, Switzerland)·2026
See all related articles
This summary is machine-generated.

This study introduces a machine learning approach for monitoring laser powder bed fusion (L-PBF) quality. A convolutional neural network (CNN) achieved 98.14% accuracy in identifying melting anomalies, improving industrial adoption.

Area of Science:

  • Materials Science
  • Manufacturing Engineering
  • Artificial Intelligence

Background:

  • Laser powder bed fusion (L-PBF) is crucial for aerospace and medical manufacturing.
  • Melting anomalies in L-PBF degrade component quality and limit industrial use.
  • Current methods struggle with accurate layer-wise melting quality recognition due to complex surface morphologies.

Purpose of the Study:

  • To develop and evaluate a machine learning-enabled in situ monitoring approach for layer-wise melting quality identification in L-PBF.
  • To compare the performance of support vector machine (SVM) and convolutional neural network (CNN) models for this task.
  • To establish a reliable technical foundation for intelligent in situ monitoring in L-PBF.

Main Methods:

  • Fabricated specimens with over-melting (OM), lack of fusion (LOF), and normal melting states by varying laser power and scanning speed.
Keywords:
defects classificationin situ monitoringlaser powder bed fusionmachine learningmelting quality recognition

More Related Videos

Automatic Laser-based Geometry Capture for Finite Element Analysis of Weld Beads
07:58

Automatic Laser-based Geometry Capture for Finite Element Analysis of Weld Beads

Published on: July 25, 2025

Quantitative Analysis of Vacuum Induction Melting by Laser-induced Breakdown Spectroscopy
03:49

Quantitative Analysis of Vacuum Induction Melting by Laser-induced Breakdown Spectroscopy

Published on: June 10, 2019

Related Experiment Videos

Last Updated: Jun 27, 2026

Real-Time Imaging of Bonding in 3D-Printed Layers
04:36

Real-Time Imaging of Bonding in 3D-Printed Layers

Published on: September 1, 2023

Automatic Laser-based Geometry Capture for Finite Element Analysis of Weld Beads
07:58

Automatic Laser-based Geometry Capture for Finite Element Analysis of Weld Beads

Published on: July 25, 2025

Quantitative Analysis of Vacuum Induction Melting by Laser-induced Breakdown Spectroscopy
03:49

Quantitative Analysis of Vacuum Induction Melting by Laser-induced Breakdown Spectroscopy

Published on: June 10, 2019

  • Captured layer-wise surface images using a high-resolution CMOS camera.
  • Constructed a dataset of 5110 images after filtering and validation, then trained and optimized SVM and CNN models.

    • Main Results:

    • The CNN model achieved a superior classification accuracy of 98.14%, compared to 96.77% for the SVM model.
    • CNN demonstrated faster inference speed (0.036 s/layer) than SVM (0.068 s/layer).
    • Crucially, the CNN model eliminated critical cross-class misclassifications between OM and LOF, unlike the SVM model.

    Conclusions:

    • Image-based machine learning, particularly CNNs, offers a robust solution for in situ L-PBF process monitoring.
    • The developed CNN model enhances accuracy, efficiency, and reliability, supporting operational decisions and reducing losses.
    • This approach has significant potential for practical deployment in industrial L-PBF settings.