Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same journal

Gene expression in visceral adipocytes in metabolically healthy and unhealthy obesity: A cross-sectional analysis of associations with cardiometabolic components.

Science progress·2026

Same journal

Proteomic profiling reveals mitochondrial metabolic alterations in dexamethasone-induced neuronal differentiation.

Science progress·2026

Same journal

Stroke risk associated with the interaction between composite dietary antioxidant index and heavy metals: A cross-sectional explainable machine learning study using NHANES data.

Science progress·2026

Same journal

Neuroimaging in schizophrenia: From group-average abnormalities to individualised circuit models.

Science progress·2026

Same journal

Clinical and mechanistic effects of GLP-1 receptor agonists in hidradenitis suppurativa and comorbidities.

Science progress·2026

Same journal

Association between serum albumin-to-globulin ratio and diabetic retinopathy: A cross-sectional study based on the 2001-2020 NHANES database.

Science progress·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Oct 12, 2025

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

Research on laser ultrasonic surface defect identification based on a support vector machine.

Chao Chen¹, Xingyuan Zhang¹

¹School of Air Transport, 66323Shanghai University of Engineering Science, Shanghai, China.

Science Progress

|November 26, 2021

Summary

This summary is machine-generated.

This study introduces a support vector machine (SVM) method for accurately measuring surface defect depth using laser ultrasonic inspection. The SVM model achieved high prediction accuracy, outperforming other methods for defect depth identification.

Keywords:

COMSOL Laser ultrasound support vector machine surface defects

More Related Videos

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

Characterization of Surface Modifications by White Light Interferometry: Applications in Ion Sputtering, Laser Ablation, and Tribology Experiments

Characterization of Surface Modifications by White Light Interferometry: Applications in Ion Sputtering, Laser Ablation, and Tribology Experiments

Published on: February 27, 2013

Related Experiment Videos

Last Updated: Oct 12, 2025

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

Characterization of Surface Modifications by White Light Interferometry: Applications in Ion Sputtering, Laser Ablation, and Tribology Experiments

Characterization of Surface Modifications by White Light Interferometry: Applications in Ion Sputtering, Laser Ablation, and Tribology Experiments

Published on: February 27, 2013

Area of Science:

Materials Science and Engineering
Non-Destructive Testing (NDT)
Acoustics and Ultrasonics

Background:

Quantitative identification of surface defect depth in laser ultrasonic inspection is challenging.
Existing methods may lack the required accuracy for precise defect characterization.
Advanced signal processing and machine learning are needed to improve NDT capabilities.

Purpose of the Study:

To develop a support vector machine (SVM)-based quantitative identification model for surface rectangular defect depth.
To improve the accuracy and reliability of defect depth measurement in laser ultrasonic inspection.
To compare the performance of the proposed SVM model against traditional methods.

Main Methods:

Developed a finite element model (FEM) of laser ultrasound inspection for aluminum with surface defects using COMSOL.
Simulated laser ultrasound interaction with defects of varying depths to obtain reflected wave signals.
Conducted experimental laser ultrasonic detection, collected waveforms, and extracted feature vectors (e.g., time-domain peak, center frequency peak) using MATLAB.
Established a quantitative defect depth identification model using support vector machine (SVM).

Main Results:

The SVM-based laser ultrasonic surface defect identification model demonstrated high accuracy in predicting defect depth.
The regression coefficient of determination (R²) consistently remained above 0.95.
The average relative error between predicted and true defect depths was below 10%.
The SVM model exhibited superior prediction accuracy compared to the reflection echo method and BP neural network.

Conclusions:

The proposed SVM-based method provides an accurate and reliable approach for quantitative identification of surface defect depth.
This technique significantly enhances the capabilities of laser ultrasonic inspection for material defect analysis.
The SVM model offers a promising alternative to conventional methods for NDT applications requiring precise depth measurements.