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

SINR-Based User Clustering for Downlink NOMA Systems with Limited Channel Information.

Sensors (Basel, Switzerland)·2026
Same author

Carbon Nanotube Artificial Muscles Multistimuli Actuation Mechanisms and Emerging Applications.

Small (Weinheim an der Bergstrasse, Germany)·2025
Same author

Yoke-Type Elasto-Magnetic Sensor-Based Tension Force Monitoring Method for Enhancement of Field Applicability.

Sensors (Basel, Switzerland)·2024
Same author

Three-Dimensional Engine-Based Geometric Model Optimization Algorithm for BIM Visualization with Augmented Reality.

Sensors (Basel, Switzerland)·2022
Same author

Supercritical CO<sub>2</sub>-Induced Evolution of Alkali-Activated Slag Cements.

Materials (Basel, Switzerland)·2022
Same author

Verification of Tensile Force Estimation Method for Temporary Steel Rods of FCM Bridges Based on Area of Magnetic Hysteresis Curve Using Embedded Elasto-Magnetic Sensor.

Sensors (Basel, Switzerland)·2022

Related Experiment Video

Updated: Dec 8, 2025

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

11.4K

Artificial Intelligence-Based Bolt Loosening Diagnosis Using Deep Learning Algorithms for Laser Ultrasonic Wave

Dai Quoc Tran1, Ju-Won Kim2, Kassahun Demissie Tola1

  • 1Department of Civil, Architecture and Environmental System Engineering, Sungkyunkwan University, Suwon 16419, Korea.

Sensors (Basel, Switzerland)
|September 22, 2020
PubMed
Summary

This study explores using deep learning algorithms with laser ultrasonics to detect and estimate bolted joint looseness. Signal processing significantly impacts deep learning performance for this non-destructive evaluation task.

Keywords:
acoustic emissiondigital signal processinglaser applicationsmachine learningstructural shapeswaves

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

545
Wideband Optical Detector of Ultrasound for Medical Imaging Applications
08:21

Wideband Optical Detector of Ultrasound for Medical Imaging Applications

Published on: May 11, 2014

11.6K

Related Experiment Videos

Last Updated: Dec 8, 2025

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

11.4K
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

545
Wideband Optical Detector of Ultrasound for Medical Imaging Applications
08:21

Wideband Optical Detector of Ultrasound for Medical Imaging Applications

Published on: May 11, 2014

11.6K

Area of Science:

  • Non-destructive evaluation (NDE)
  • Deep learning (DL) applications
  • Ultrasonic testing

Background:

  • Bolted joints are critical structural components.
  • Assessing joint integrity, particularly looseness, is essential for safety and performance.
  • Traditional NDE methods may have limitations in detecting subtle looseness.

Purpose of the Study:

  • To investigate the application of deep learning algorithms for detecting and estimating looseness in bolted joints.
  • To utilize a laser ultrasonic technique for data acquisition.
  • To explore the relationship between contact area and guided wave energy loss.

Main Methods:

  • Utilized a Q-switched Nd:YAG pulsed laser and acoustic emission sensor for ultrasonic signal generation and sensing.
  • Created 3D full-field ultrasonic datasets via ultrasonic wave propagation imaging (UWPI).
  • Applied signal processing techniques and a deep convolutional neural network (DCNN) with a VGG-like architecture for regression analysis.

Main Results:

  • The proposed approach demonstrated potential for integrating laser-generated ultrasound and deep learning algorithms.
  • Compared DCNN performance across different processed datasets, calculating estimated error.
  • The study highlighted the significant impact of signal processing techniques on DL performance for automatic looseness estimation.

Conclusions:

  • Deep learning algorithms show promise for non-destructive evaluation of bolted joint integrity.
  • Laser-generated ultrasound combined with DL offers a viable method for looseness detection.
  • Optimized signal processing is crucial for enhancing the accuracy of DL-based NDE.