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

Microcracking in Concrete01:20

Microcracking in Concrete

103
Microcracking in concrete refers to the tiny cracks that can form within the material even before any external load is applied. These microcracks typically occur at the interface between the coarse aggregate and the hydrated cement paste, often as a result of differential volume changes prompted by variations in stress-strain behavior, as well as thermal and moisture movement. Initially, these microcracks remain stable and do not grow substantially until the concrete is stressed to about 30...
103

You might also read

Related Articles

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

Sort by
Same author

CAD-Based Analysis and Experimental Validation of Registration Errors in Imageless Total Knee Arthroplasty.

Journal of clinical medicine·2026
Same author

A Hybrid Deep Transfer Learning Framework for Delamination Identification in Composite Laminates.

Sensors (Basel, Switzerland)·2025
Same author

Flame Retardancy and Heat Shielding in Green Polypropylene Composites Using Biohybrid Fibers and Agro-Waste Fillers.

ACS applied bio materials·2025
Same author

Damage Localization and Severity Assessment in Composite Structures Using Deep Learning Based on Lamb Waves.

Sensors (Basel, Switzerland)·2025
Same author

A Review on Traditional and Artificial Intelligence-Based Preservation Techniques for Oil Painting Artworks.

Gels (Basel, Switzerland)·2024
Same author

Energy Storage Application of CaO/Graphite Nanocomposite Powder Obtained from Waste Eggshells and Used Lithium-Ion Batteries as a Sustainable Development Approach.

Nanomaterials (Basel, Switzerland)·2024

Related Experiment Video

Updated: Jun 8, 2025

Author Spotlight: Enhancing Fiber Composite Laminate Quality with the Wet Hand Lay-Up/Vacuum Bag Process
09:54

Author Spotlight: Enhancing Fiber Composite Laminate Quality with the Wet Hand Lay-Up/Vacuum Bag Process

Published on: June 30, 2023

2.0K

Deep Learning-Based Microscopic Damage Assessment of Fiber-Reinforced Polymer Composites.

Muhammad Muzammil Azad1, Atta Ur Rehman Shah2, M N Prabhakar3

  • 1Department of Mechanical, Robotics and Energy Engineering, Dongguk University-Seoul, 30 Pildong-ro 1-gil, Jung-gu, Seoul 04620, Republic of Korea.

Materials (Basel, Switzerland)
|November 9, 2024
PubMed
Summary

This study introduces a deep learning approach for autonomous microscopic damage assessment in fiber-reinforced polymers (FRPs). EfficientNet achieved 97.75% accuracy in classifying five failure modes, offering a faster, more consistent alternative to manual analysis.

Keywords:
damage assessmentdeep learningfiber-reinforced polymersmicroscopic damagescanning electron microscopytransfer learning

More Related Videos

A Testing Platform for Durability Studies of Polymers and Fiber-reinforced Polymer Composites under Concurrent Hygrothermo-mechanical Stimuli
07:15

A Testing Platform for Durability Studies of Polymers and Fiber-reinforced Polymer Composites under Concurrent Hygrothermo-mechanical Stimuli

Published on: December 11, 2014

13.8K
Disentangling High Strength Copolymer Aramid Fibers to Enable the Determination of Their Mechanical Properties
06:02

Disentangling High Strength Copolymer Aramid Fibers to Enable the Determination of Their Mechanical Properties

Published on: September 1, 2018

7.1K

Related Experiment Videos

Last Updated: Jun 8, 2025

Author Spotlight: Enhancing Fiber Composite Laminate Quality with the Wet Hand Lay-Up/Vacuum Bag Process
09:54

Author Spotlight: Enhancing Fiber Composite Laminate Quality with the Wet Hand Lay-Up/Vacuum Bag Process

Published on: June 30, 2023

2.0K
A Testing Platform for Durability Studies of Polymers and Fiber-reinforced Polymer Composites under Concurrent Hygrothermo-mechanical Stimuli
07:15

A Testing Platform for Durability Studies of Polymers and Fiber-reinforced Polymer Composites under Concurrent Hygrothermo-mechanical Stimuli

Published on: December 11, 2014

13.8K
Disentangling High Strength Copolymer Aramid Fibers to Enable the Determination of Their Mechanical Properties
06:02

Disentangling High Strength Copolymer Aramid Fibers to Enable the Determination of Their Mechanical Properties

Published on: September 1, 2018

7.1K

Area of Science:

  • Materials Science
  • Mechanical Engineering
  • Computer Science

Background:

  • Fiber-reinforced polymers (FRPs) offer superior strength-to-weight ratios but exhibit complex orthotropic properties leading to diverse damage modes.
  • Microscopic damage assessment in FRPs, crucial for design and application, traditionally relies on labor-intensive manual analysis of scanning electron microscopy (SEM) images.
  • Manual SEM image analysis is time-consuming, subjective, and prone to inter-observer variability, hindering efficient material characterization.

Purpose of the Study:

  • To develop and evaluate a deep learning-based method for the autonomous microscopic damage assessment of FRPs.
  • To compare the performance of several pre-trained deep learning models for classifying distinct FRP failure modes.
  • To establish an efficient, consistent, and scalable solution for damage assessment, reducing reliance on manual expertise.

Main Methods:

  • Utilized computationally efficient pre-trained deep learning models: DenseNet121, NasNet Mobile, EfficientNet, and MobileNet.
  • Trained and validated models on a dataset of SEM images of FRPs exhibiting five failure modes: fiber breakage, fiber pullout, mixed-mode, matrix brittle, and matrix ductile failure.
  • Assessed model performance using various metrics on an unseen test dataset to determine classification accuracy for each failure mode.

Main Results:

  • The EfficientNet model demonstrated the highest classification accuracy, achieving 97.75% for identifying the five distinct failure modes.
  • All evaluated deep learning models showed promising performance in autonomously classifying microscopic damage in FRPs.
  • The deep learning approach significantly reduced the need for manual interpretation of SEM images.

Conclusions:

  • Deep learning techniques provide an effective and efficient solution for the autonomous microscopic damage assessment of fiber-reinforced polymers.
  • The proposed method offers improved consistency and scalability compared to traditional manual analysis of SEM images.
  • This research paves the way for faster and more reliable material characterization and design optimization of FRPs.