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: Nov 10, 2025

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

Additive Manufacturing-Enabled Low-Cost Particle Detector

Published on: March 24, 2023

2.0K

FPGA-Based Acceleration on Additive Manufacturing Defects Inspection.

Yawen Luo1, Yuhua Chen1

  • 1Department of Electrical and Computer Engineering, University of Houston, Houston, TX 77204, USA.

Sensors (Basel, Switzerland)
|April 3, 2021
PubMed
Summary
This summary is machine-generated.

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

Electrodermal Temperature-Adjusted Electrodermal Activity (EDA) for Stress Detection in Virtual Reality.

Sensors (Basel, Switzerland)·2026
Same author

The Untapped Potential of Ascon Hash Functions: Benchmarking, Hardware Profiling, and Application Insights for Secure IoT and Blockchain Systems.

Sensors (Basel, Switzerland)·2025
Same author

Virtual Reality as a Stress Measurement Platform: Real-Time Behavioral Analysis with Minimal Hardware.

Sensors (Basel, Switzerland)·2025
Same author

DARTPHROG: A Superscalar Homomorphic Accelerator.

Sensors (Basel, Switzerland)·2025
Same author

Cost-Effective Network Reordering Using FPGA.

Sensors (Basel, Switzerland)·2023
Same author

Review of State-of-the-Art FPGA Applications in IoT Networks.

Sensors (Basel, Switzerland)·2022
Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026
Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026
Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026
Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026
Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026
Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026
See all related articles

This study introduces a real-time defect detection system for additive manufacturing (AM). Utilizing a binarized neural network (BNN) on Field Programmable Gate Arrays (FPGAs), it achieves high accuracy in identifying defects, enabling cost reduction.

Area of Science:

  • Manufacturing Engineering
  • Computer Vision
  • Artificial Intelligence

Background:

  • Additive manufacturing (AM) offers advantages over traditional methods but is prone to internal defects.
  • Real-time inspection is crucial for defect identification to minimize costs through process abortion or repair.
  • Existing inspection methods may lack the speed and accuracy required for immediate feedback during AM.

Purpose of the Study:

  • To develop a high-accuracy, real-time defect detection system for additive manufacturing processes.
  • To leverage Field Programmable Gate Arrays (FPGAs) for accelerating defect classification.
  • To implement a binarized neural network (BNN) optimized for FPGA hardware.

Main Methods:

  • A defects database (NEU-DET) was used for training a Convolutional Neural Network (CNN).
Keywords:
FPGAadditive manufacturingbinarized neural networkconvolutional neural networkdefects inspectionselective search

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

390
Author Spotlight: Introduction to Active Probe Atomic Force Microscopy with Quattro-Parallel Cantilever Arrays
05:04

Author Spotlight: Introduction to Active Probe Atomic Force Microscopy with Quattro-Parallel Cantilever Arrays

Published on: June 13, 2023

2.0K

Related Experiment Videos

Last Updated: Nov 10, 2025

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

Additive Manufacturing-Enabled Low-Cost Particle Detector

Published on: March 24, 2023

2.0K
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

390
Author Spotlight: Introduction to Active Probe Atomic Force Microscopy with Quattro-Parallel Cantilever Arrays
05:04

Author Spotlight: Introduction to Active Probe Atomic Force Microscopy with Quattro-Parallel Cantilever Arrays

Published on: June 13, 2023

2.0K
  • A Binarized Neural Network (BNN) was designed for efficient FPGA implementation.
  • Selective search and non-maximum suppression algorithms were used for defect localization.
  • FPGA hardware was utilized for real-time acceleration of the BNN model.

    • Main Results:

    • The BNN model achieved 97.9% accuracy in classifying images as defective or defect-free on the NEU-DET dataset.
    • The FPGA-based BNN module processed images at a speed of 0.5 seconds per image.
    • The BNN design demonstrated modularity, allowing for parallelization to maximize FPGA resource utilization.

    Conclusions:

    • The proposed FPGA-based BNN system enables accurate and real-time defect inspection in additive manufacturing.
    • The modular design facilitates scalability for larger FPGA implementations.
    • This technology can significantly reduce costs associated with undetected defects in AM parts.