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

Mechanical Characteristics of Steel

Mechanical Characteristics of Steel

The mechanical characteristics of steel are assessed through various tests that evaluate its strength, toughness, and flexibility. These tests include tension, torsion, impact, bending, and hardness assessments, each providing crucial information about steel's suitability for specific applications.
The tension test is fundamental for determining tensile strength. In this test, a steel specimen is stretched using a gripping device until it breaks. The data collected during this test are used...

You might also read

Related Articles

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

Sort by

Same author

Interfacial interactions in CL-20/alloy-metal/polymer energetic composites: a molecular dynamics study.

Journal of molecular modeling·2026

Same author

Evolution of an adaptive, inducible defensive trait in a model crustacean.

Genome research·2026

Same author

Role of diagnostic testing in reducing unnecessary antibiotic use for upper respiratory tract infections in Chinese primary healthcare: a mixed-methods study.

BMC primary care·2026

Same author

Spent Mushroom Substrate Reused as Organic Fertilizer Enhances Lettuce (<i>Lactuca sativa</i> L.) Quality and Soil Nutrients: Insights from Physicochemical and Microbiome Analyses.

Microorganisms·2026

Same author

Evaluation of different types of isotope-labelled steroids based on liquid chromatography-mass spectrometry.

Isotopes in environmental and health studies·2026

Same author

Structural Design and Advanced Diagnostics of Lithium Metal Anodes for High-Energy-Density Batteries.

Chemistry, an Asian journal·2026

Search research articles

Related Experiment Video

Updated: Mar 15, 2026

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

A Lightweight Model for Hot-Rolled Steel Strip Surface Defect Recognition.

Naixuan Guo^1,2, Haonan Fan¹, Qin Dong^1,2

¹School of Information Engineering, Yancheng Institute of Technology, Yancheng 224051, China.

Sensors (Basel, Switzerland)

|March 14, 2026

Summary

A new lightweight dual-surface defect recognition model for hot-rolled steel strips enables mobile applications. This optimized model achieves high accuracy on low-power devices, improving industrial automation.

Keywords:

convolutional neural network data augmentation defect recognition image classification network slimming

More Related Videos

Full-field Strain Measurements for Microstructurally Small Fatigue Crack Propagation Using Digital Image Correlation Method

Full-field Strain Measurements for Microstructurally Small Fatigue Crack Propagation Using Digital Image Correlation Method

Published on: January 16, 2019

Applicability Analysis of Assessment Methods for Morphological Parameters of Corroded Steel Bars

Applicability Analysis of Assessment Methods for Morphological Parameters of Corroded Steel Bars

Published on: November 1, 2018

Related Experiment Videos

Last Updated: Mar 15, 2026

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

Full-field Strain Measurements for Microstructurally Small Fatigue Crack Propagation Using Digital Image Correlation Method

Full-field Strain Measurements for Microstructurally Small Fatigue Crack Propagation Using Digital Image Correlation Method

Published on: January 16, 2019

Applicability Analysis of Assessment Methods for Morphological Parameters of Corroded Steel Bars

Applicability Analysis of Assessment Methods for Morphological Parameters of Corroded Steel Bars

Published on: November 1, 2018

Area of Science:

Intelligent Manufacturing and Industrial Automation
Computer Vision and Machine Learning

Background:

Current hot-rolled strip steel defect detection systems are often stationary, expensive, and energy-intensive, limiting mobile applications.
The need for efficient and accurate defect detection is critical for intelligent manufacturing and industrial automation.

Purpose of the Study:

To design and propose a lightweight dual-surface defect recognition model for hot-rolled steel strips.
To enable the implementation of defect detection on mobile, low-power devices like Raspberry Pi.

Main Methods:

Augmented the NEU-CLS dataset using StyleGAN3 for image generation, a water-wave-like algorithm for denoising, and Real-ESRGAN for super-resolution.
Applied Network Slimming algorithm for pruning MMAM-EfficientNet-B0 during training, removing 70% of the network structure.
Deployed the optimized model on a Raspberry Pi for real-time defect recognition.

Main Results:

Achieved a high accuracy of 96.333% for defect recognition on the Raspberry Pi.
Reduced classification time per image to 1.527 seconds, a significant improvement over the original model.
Demonstrated the model's real-time effectiveness and practical value for mobile applications.

Conclusions:

The proposed lightweight dual-surface defect recognition model is effective for hot-rolled strip steel.
The model's successful deployment on low-power devices validates its suitability for mobile and outdoor industrial applications.
This research contributes to advancing intelligent manufacturing through efficient and accessible defect detection solutions.