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 author

Spatial comparison and prognostic significance of macrophages in matched primary colorectal cancer and liver metastases: a retrospective study.

Scientific reports·2026

Same author

Fibroblast Mitochondrial Ca2+ Overload Drives Skin Fibrosis via mtDNA Leakage and cGAS-STING Activation in Systemic Sclerosis.

Arthritis & rheumatology (Hoboken, N.J.)·2026

Same author

Genome-wide identification, characterization, and expression analysis of the plant defensin (PDF) gene family in soybean.

BMC plant biology·2026

Same author

Space-Dependent Oviposition Preference in Drosophila.

Neuroscience bulletin·2026

Same author

CCR2-Guided T<sub>reg</sub> Exosome-Gas6 Hybrid Synergistically Reprograms Macrophage Inflammation and Immune Tolerance in Gouty Arthritis.

Advanced healthcare materials·2026

Same author

Oral myiasis complicating endotracheal intubation in a diabetic patient: a case report.

Frontiers in endocrinology·2026

Search research articles

Related Experiment Video

Updated: Jun 17, 2025

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

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

Published on: December 15, 2023

Concrete Defect Localization Based on Multilevel Convolutional Neural Networks.

Yameng Wang¹, Lihua Wang¹, Wenjing Ye¹

¹School of Aerospace Engineering and Applied Mechanics, Tongji University, Shanghai 200092, China.

Materials (Basel, Switzerland)

|August 10, 2024

Summary

This summary is machine-generated.

This study introduces a multilevel convolutional neural network (CNN) with array ultrasonic testing (AUT) to accurately locate defects in concrete structures. The enhanced method improves defect detection accuracy and efficiency, offering a robust solution for structural health monitoring.

Keywords:

array ultrasonic testing concrete structures convolutional neural networks defect localization

More Related Videos

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

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Related Experiment Videos

Last Updated: Jun 17, 2025

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

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

Published on: December 15, 2023

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

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Area of Science:

Civil Engineering
Materials Science
Artificial Intelligence

Background:

Concrete structures are prone to defects from design, construction, and environmental factors.
Accurate defect detection is crucial for structural integrity and safety.
Traditional methods struggle with complex structures and hidden defects.

Purpose of the Study:

To propose a novel method for identifying and locating hole defects in concrete structures.
To enhance the accuracy and efficiency of defect detection compared to traditional approaches.
To develop a system that automatically interprets ultrasonic signals for defect localization.

Main Methods:

Utilized array ultrasonic testing (AUT) to collect ultrasonic signals from concrete structures.
Employed a multilevel convolutional neural network (CNN) for progressive defect localization.
Simulated AUT detection using COMSOL-Multiphysics to generate extensive training data.

Main Results:

The proposed multilevel CNN-AUT method achieved a defect localization accuracy of 95.27%, an improvement from 85.38% with traditional CNNs.
Demonstrated reduced computation time, indicating increased operational efficiency.
Verified strong robustness in recognizing noisy ultrasonic signals through experimental testing.

Conclusions:

The multilevel CNN-AUT approach offers a highly accurate and efficient solution for concrete defect detection.
This method effectively addresses limitations of traditional techniques, especially for complex or hidden defects.
The findings provide a valuable reference for future structural health monitoring and non-destructive testing.