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

Accurate Ultrasonic Thickness Measurement for Arbitrary Time-Variant Thermal Profile.

Sensors (Basel, Switzerland)·2024
Same author

Large-area inspection of defects in metal plates using multi-mode guided acoustic waves and sparse sensor networks.

Ultrasonics·2024
Same author

Void-Engineered Metamaterial Delay Line with Built-In Impedance Matching for Ultrasonic Applications.

Sensors (Basel, Switzerland)·2024
Same author

Ultrasonic Testing of Mechanical Changes in a Water-Filled Pipe with Multi-Mode and Broadband Signals and Two-Level Compensation.

Sensors (Basel, Switzerland)·2022
Same author

Thermodynamics, dynamics, and structure of supercritical water at extreme conditions.

Physical chemistry chemical physics : PCCP·2020
Same author

Electrical conductivity, ion pairing, and ion self-diffusion in aqueous NaCl solutions at elevated temperatures and pressures.

The Journal of chemical physics·2019
Same journal

CFREE-uPIV: A contrast-free resolution-enhanced ultrasound particle image velocimetry for rapid microvascular flow imaging.

Ultrasonics·2026
Same journal

Ultrasonic-induced nucleation kinetics in directed energy deposition.

Ultrasonics·2026
Same journal

Grain size evaluation in polycrystalline materials using the interference effect of bounded ultrasonic beams at the Rayleigh critical angle.

Ultrasonics·2026
Same journal

Ultrasonic characterization of functionally graded materials using a continuously graded model and spectral inversion.

Ultrasonics·2026
Same journal

Frequency-wavenumber domain inversion for arterial viscoelasticity.

Ultrasonics·2026
Same journal

Pressure- and frequency-dependent acoustic behavior of second-generation acoustic reporter genes-expressing bacteria for optimized ultrasound imaging.

Ultrasonics·2026
See all related articles

Related Experiment Video

Updated: Jun 22, 2025

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

515

Multi-level structural damage characterization using sparse acoustic sensor networks and knowledge transferred deep

Rajendra P Palanisamy1, Do-Kyung Pyun1, Alp T Findikoglu1

  • 1Materials Physics and Applications (MPA), Los Alamos National Laboratory, Los Alamos, NM 87545, USA.

Ultrasonics
|June 30, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces a machine learning approach for structural health monitoring in complex structures, significantly improving defect diagnosis accuracy. The method enhances knowledge transfer, reducing data needs and boosting inspection efficiency.

Keywords:
Acoustic sensor networkAdaptive convolutionData-driven structural health monitoringKnowledge transfer deep learningNetwork spatial assistant (NSA)Sparsity of training data

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

6.1K
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

1.0K

Related Experiment Videos

Last Updated: Jun 22, 2025

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

515
Data Acquisition Protocol for Determining Embedded Sensitivity Functions
07:46

Data Acquisition Protocol for Determining Embedded Sensitivity Functions

Published on: April 20, 2016

6.1K
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

1.0K

Area of Science:

  • Engineering
  • Materials Science
  • Artificial Intelligence

Background:

  • Standard structural health monitoring (SHM) methods struggle with complex structures, necessitating advanced techniques.
  • Data-driven machine learning for SHM requires extensive training datasets, which are challenging to acquire for diverse defects.
  • Knowledge transfer in neural networks can reduce data requirements and computational costs for SHM systems.

Purpose of the Study:

  • To demonstrate a machine learning-based multi-level damage characterization method with knowledge transfer capabilities for sparse sensor networks.
  • To introduce novel techniques for efficient knowledge transfer within deep learning algorithms for SHM.
  • To evaluate the proposed method's effectiveness in defect localization and severity assessment on complex structures.

Main Methods:

  • Development of a machine learning-based damage characterization framework utilizing a sparse sensor network.
  • Implementation of a novel network spatial assistance and adaptive convolution technique for efficient knowledge transfer.
  • Experimental validation on an aluminum plate with induced defects, analyzing multiply scattered waves.

Main Results:

  • The proposed method improved knowledge-transferred damage characterization by 50% in localization and 24% in severity assessment.
  • Multiply scattered waves were found to contain rich defect signatures, enhancing identification and quantification accuracy.
  • A 100% prediction accuracy was achieved for all damage characterization levels using multiply scattered waves with a fixed sensor network.

Conclusions:

  • Machine learning with knowledge transfer offers a powerful solution for SHM in complex structures, overcoming limitations of traditional methods.
  • The proposed adaptive convolution and spatial assistance techniques facilitate efficient knowledge transfer, reducing the need for large datasets.
  • Utilizing multiply scattered waves in SHM significantly enhances defect detection and quantification accuracy, paving the way for more reliable inspection systems.