EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AI-Based Defect Detection and Classification Techniques for Leak-Proof Industrial Surfaces

Dr. J. Noorul Ameen M.E, Ph.D., Manibharathi S

International Journal of Scientific Research in Computer Science, Engineering and Information Technology · 12.04.2026 · 12 (2) · 488-496

DOI: 10.32628/cseit26121377 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Scientific Research in Computer Science, Engineering and Information Technology, online erschienen am 12.04.2026. Verfasst von Dr. J. Noorul Ameen M.E und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Ensuring the structural integrity of industrial pipelines is essential for the safe and efficient transportation of fluids across large-scale networks. Conventional inspection techniques, including manual assessments and specialized tools, often involve high operational costs, extended inspection time, and susceptibility to human error, limiting their effectiveness for continuous monitoring. This paper presents an AI-based defect detection and classification approach for leak-proof industrial surfaces using the YOLO object detection algorithm. High-resolution images acquired from drones, cameras, or robotic platforms are processed through advanced preprocessing techniques to enhance feature visibility. The trained YOLO model identifies and classifies defects such as cracks, corrosion, dents, and leaks with high precision and speed. The automated framework enables real-time detection and accurate localization of anomalies, significantly improving inspection efficiency. Furthermore, the system incorporates an alert mechanism that generates immediate notifications and detailed reports, facilitating prompt maintenance actions. The proposed approach enhances reliability, reduces human intervention, and supports scalable monitoring of extensive pipeline networks. By integrating intelligent computer vision techniques, this research contributes to improved safety standards, minimized environmental risks, and proactive maintenance strategies in industrial infrastructure.

Zitieren

APA

M.E, D. J. N. A., Ph.D., & S, M. (2026). AI-Based Defect Detection and Classification Techniques for Leak-Proof Industrial Surfaces. International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 12(2), 488-496. https://doi.org/10.32628/cseit26121377

Vancouver

M.E DJNA, Ph.D., S M. AI-Based Defect Detection and Classification Techniques for Leak-Proof Industrial Surfaces. International Journal of Scientific Research in Computer Science, Engineering and Information Technology. 2026;12(2):488-496. doi:10.32628/cseit26121377

BibTeX
@article{ME2026,
  author = {M.E, Dr. J. Noorul Ameen and Ph.D. and S, Manibharathi},
  title = {AI-Based Defect Detection and Classification Techniques for Leak-Proof Industrial Surfaces},
  journal = {International Journal of Scientific Research in Computer Science, Engineering and Information Technology},
  year = {2026},
  volume = {12},
  number = {2},
  pages = {488--496},
  doi = {10.32628/cseit26121377}
}
Kostenlos starten →