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

Acoustic emission based corrosion imaging as a possible method for identification of localized atmospheric corrosion of aluminum structures.

Ultrasonics·2025
Same author

Single-shot capable surface acoustic wave dispersion measurement of a layered plate.

The Review of scientific instruments·2025
Same author

Assessing the Adhesiveness and Long-Term Behaviour of Piezoresistive Strain Sensor Materials for Application in Structural Health Monitored Structures.

Sensors (Basel, Switzerland)·2025
Same author

Damage Identification Using Measured and Simulated Guided Wave Damage Interaction Coefficients Predicted Ad Hoc by Deep Neural Networks.

Sensors (Basel, Switzerland)·2025
Same author

Prediction of the Released Mechanical Energy of Loaded Lap Shear Joints by Acoustic Emission Measurements.

Sensors (Basel, Switzerland)·2024
Same author

Simultaneous laser ultrasonic measurement of sound velocities and thickness of plates using combined mode local acoustic spectroscopy.

Ultrasonics·2024

Related Experiment Video

Updated: Sep 24, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.3K

Damage identification using wave damage interaction coefficients predicted by deep neural networks.

Christoph Humer1, Simon Höll1, Christoph Kralovec1

  • 1Institute of Structural Lightweight Design, Johannes Kepler University Linz, Altenberger Str. 69, Linz, 4040, Upper Austria, Austria.

Ultrasonics
|May 2, 2022
PubMed
Summary
This summary is machine-generated.

A new method uses deep neural networks (DNNs) to enhance structural health monitoring (SHM) by predicting wave damage interaction coefficients (WDICs) for lightweight structures. This improves damage identification accuracy and efficiency.

Keywords:
Damage identificationDeep neural networksGuided wavesNon-reflective boundariesStructural health monitoringWave damage interaction coefficients

More Related Videos

Data Acquisition Protocol for Determining Embedded Sensitivity Functions
07:46

Data Acquisition Protocol for Determining Embedded Sensitivity Functions

Published on: April 20, 2016

6.2K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

656

Related Experiment Videos

Last Updated: Sep 24, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.3K
Data Acquisition Protocol for Determining Embedded Sensitivity Functions
07:46

Data Acquisition Protocol for Determining Embedded Sensitivity Functions

Published on: April 20, 2016

6.2K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

656

Area of Science:

  • Engineering
  • Materials Science
  • Computational Mechanics

Background:

  • Lightweight structures require damage-tolerant design for safety and reliability.
  • Structural health monitoring (SHM) is crucial for assessing structural integrity.
  • Guided wave methods using piezoelectric transducers are effective for thin-walled structures.

Purpose of the Study:

  • To present a novel damage identification method for plate-like structures using a database of wave damage interaction coefficients (WDICs).
  • To enhance the generation of WDIC patterns through deep neural networks (DNNs) for improved database completeness.
  • To enable accurate damage identification with low computational cost.

Main Methods:

  • Numerical simulation of damages using finite elements to generate initial WDIC patterns.
  • Application of deep neural networks (DNNs) for smart interpolation and expansion of the WDIC database.
  • Verification using time-domain simulations and statistical analysis of identification rates.

Main Results:

  • DNNs significantly enhance the WDIC database by predicting coefficients for unseen damages.
  • DNNs demonstrate superior performance in interpolating complex WDIC patterns compared to other machine learning algorithms.
  • The proposed method accurately identifies damage characteristics with high confidence.

Conclusions:

  • Deep neural networks offer an efficient and accurate approach to expanding SHM databases.
  • The developed WDIC-based method effectively identifies damage in plate-like structures.
  • This technique contributes to safer and more reliable lightweight structures through advanced SHM.