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 Experiment Videos

Prediction of Damage Distribution in Gas Cylinder Stages Based on Semi-Supervised and Transfer Learning Algorithms.

Xiangdong Ma1, Zhigang Gao1, Wenli Dong1

  • 1Special Equipment Safety Supervision Inspection Institute of Jiangsu Province, Nanjing 210036, China.

Sensors (Basel, Switzerland)
|July 15, 2026
PubMed
Summary

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

Spectroscopic diagnosis of laryngeal carcinoma using near-infrared Raman spectroscopy and random recursive partitioning ensemble techniques.

The Analyst·2009
Same author

Importance of mitochondria in manganese-induced cellular toxicity.

Neurotoxicology·2009
Same author

Pregnancy, childrearing, and risk of stroke in Chinese women.

Stroke·2009
Same author

Matrix metalloproteinase-2 polymorphisms and breast cancer susceptibility.

Cancer epidemiology, biomarkers & prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology·2009
Same author

No association between matrix metalloproteinase (MMP)-1, MMP-3, and MMP-7 SNPs and endometrial cancer risk.

Cancer epidemiology, biomarkers & prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology·2009
Same author

Polymorphisms in tissue inhibitors of metalloproteinases-2 and -3 and breast cancer susceptibility and survival.

International journal of cancer·2009

A new semi-supervised algorithm improves fiber-reinforced composite cylinder damage classification using acoustic emission (AE) signals. This method achieves 85.92% accuracy, significantly outperforming traditional techniques for structural health monitoring.

Area of Science:

  • Materials Science
  • Mechanical Engineering
  • Structural Health Monitoring

Background:

  • Clustering algorithms are commonly used for fiber-reinforced composite cylinder damage classification.
  • Current methods face challenges in accurately categorizing damage types due to evaluation criteria influencing cluster numbers.
  • A need exists for more precise damage classification methods in composite structures.

Purpose of the Study:

  • To develop a semi-supervised algorithm for enhanced damage classification in fiber-reinforced composite cylinders.
  • To improve the accuracy of damage type categorization using limited labeled data.
  • To validate the proposed algorithm against traditional methods.

Main Methods:

  • A phased pressurization experiment was conducted on fiber-reinforced composite cylinders.
Keywords:
fiber-reinforced composite cylindermean-teacher network structureprediction of damage distributionsemi-supervisedtransfer learning algorithms

Related Experiment Videos

  • Damage signals were captured using acoustic emission (AE) hits, with burst-type hits analyzed.
  • A mean-teacher semi-supervised network leveraging transfer learning was constructed and trained on marked AE hits.

    • Main Results:

    • The semi-supervised algorithm achieved a classification accuracy of 85.92%.
    • This represents a significant improvement compared to traditional supervised learning and clustering algorithms.
    • Accuracy increased by nearly 30% over existing methods.

    Conclusions:

    • The proposed semi-supervised approach effectively enhances damage classification for composite cylinders.
    • This method provides higher damage classification information with a minimal number of labels.
    • The findings offer a promising advancement for structural health monitoring of composite materials.