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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Negative Pressure Wound Therapy Modulates Wound pH and Bacterial Invasion in <i>Pseudomonas aeruginosa-</i>infected Porcine Wounds.

Plastic and reconstructive surgery. Global open·2026
Same author

Integrative multi-omics implicates a CTSB/ITIH-ECM axis in autism spectrum disorder.

Neurobiology of disease·2026
Same author

Endothelial SMAD1-MCAM axis facilitates sunitinib resistance and progression of clear cell renal cell carcinoma via LAMB1-ITGB1 signaling.

Drug resistance updates : reviews and commentaries in antimicrobial and anticancer chemotherapy·2026
Same author

Insights into the mechanisms of drug resistance in renal cell carcinoma: from multi-omics perspective.

International journal of surgery (London, England)·2026
Same author

Advances in Nanotechnology-Based Topical Delivery Systems for Skincare Applications.

Pharmaceutics·2026
Same author

Single-cell profiling of bone metastasis ecosystems reveals pivotal role of INSR<sup>+</sup>AEC in clear cell renal cell carcinoma.

Translational oncology·2025

Related Experiment Video

Updated: Jul 5, 2025

Additive Manufacturing-Enabled Low-Cost Particle Detector
06:05

Additive Manufacturing-Enabled Low-Cost Particle Detector

Published on: March 24, 2023

1.3K

A Real-Time Defect Detection Strategy for Additive Manufacturing Processes Based on Deep Learning and Machine Vision

Wei Wang1, Peiren Wang1, Hanzhong Zhang1

  • 1Key Laboratory of MEMS of the Ministry of Education, Southeast University, Nanjing 210096, China.

Micromachines
|January 23, 2024
PubMed
Summary

This study introduces a deep learning defect detection system for additive manufacturing (AM). The enhanced YOLOv8 model accurately identifies fabrication flaws in 3D microelectronics, improving product quality and reliability.

Keywords:
additive manufacturingdeep learningdefect detectionmachine vision

More Related Videos

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography
11:34

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

11.1K
Author Spotlight: Real-Time Imaging of Bonding in 3D-Printed Layers
04:36

Author Spotlight: Real-Time Imaging of Bonding in 3D-Printed Layers

Published on: September 1, 2023

3.3K

Related Experiment Videos

Last Updated: Jul 5, 2025

Additive Manufacturing-Enabled Low-Cost Particle Detector
06:05

Additive Manufacturing-Enabled Low-Cost Particle Detector

Published on: March 24, 2023

1.3K
Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography
11:34

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

11.1K
Author Spotlight: Real-Time Imaging of Bonding in 3D-Printed Layers
04:36

Author Spotlight: Real-Time Imaging of Bonding in 3D-Printed Layers

Published on: September 1, 2023

3.3K

Area of Science:

  • Materials Science and Engineering
  • Computer Science
  • Electrical Engineering

Background:

  • Additive Manufacturing (AM) is evolving towards producing high-value, functional end-use products, including complex 3D microelectronics.
  • The intricate nature of AM processes for 3D microelectronics increases the risk of fabrication defects and product failure.
  • Real-time defect detection is crucial for ensuring the quality and reliability of advanced AM products.

Purpose of the Study:

  • To develop and evaluate a deep learning-based defect detection technology for real-time monitoring of AM fabrication processes.
  • To address the challenge of fabrication defects in complex 3D microelectronic products manufactured via AM.
  • To enhance the reliability and quality control of multi-material and complex structure AM.

Main Methods:

  • Proposed an enhanced YOLOv8 algorithm for training a deep learning model focused on defect identification and evaluation.
  • Utilized machine vision techniques for real-time monitoring during the AM fabrication process.
  • Created a tailored dataset of 3550 images covering four typical defect categories from extrusion 3D printing.

Main Results:

  • The enhanced YOLOv8 model achieved a high mean average precision (mAP50) of 91.7% for defect detection.
  • The system operated at a real-time frame rate of 71.9 frames per second, suitable for in-process monitoring.
  • Demonstrated the feasibility of the proposed deep learning approach for identifying and evaluating defects in AM.

Conclusions:

  • The developed deep learning-based defect detection system effectively identifies fabrication defects in AM processes.
  • The enhanced YOLOv8 model offers a promising solution for real-time quality control in 3D microelectronics manufacturing.
  • This technology can significantly reduce product failure rates and improve the overall reliability of advanced AM products.