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

You might also read

Related Articles

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

Sort by
Same author

Explainable Fault Classification and Severity Diagnosis in Rotating Machinery Using Kolmogorov-Arnold Networks.

Entropy (Basel, Switzerland)·2025
Same author

Insights into Object Semantics: Leveraging Transformer Networks for Advanced Image Captioning.

Sensors (Basel, Switzerland)·2024
Same author

Multi-Modal Song Mood Detection with Deep Learning.

Sensors (Basel, Switzerland)·2022
See all related articles

Related Experiment Video

Updated: Jun 14, 2025

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator
06:45

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator

Published on: October 28, 2022

1.6K

An End-to-End Deep Learning Framework for Fault Detection in Marine Machinery.

Spyros Rigas1, Paraskevi Tzouveli2, Stefanos Kollias2

  • 1Department of Digital Industry Technologies, School of Science, National and Kapodistrian University of Athens, 34400 Psachna, Greece.

Sensors (Basel, Switzerland)
|August 29, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces a new deep learning (DL) framework for predictive maintenance (PdM) in maritime operations. It uses Graph Attention Networks (GATs) for accurate and timely fault detection in shipboard machinery.

Keywords:
MLOpsdata collectiondata engineeringdeep learningfault detectionmarine IoTmultivariate time series

More Related Videos

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.0K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

492

Related Experiment Videos

Last Updated: Jun 14, 2025

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator
06:45

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator

Published on: October 28, 2022

1.6K
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.0K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

492

Area of Science:

  • Industrial Internet of Things (IIoT)
  • Maritime Operations
  • Artificial Intelligence

Background:

  • IIoT enables vast data integration in industries like maritime.
  • Cloud computing and deep learning (DL) are optimizing maritime operations, especially Predictive Maintenance (PdM).

Purpose of the Study:

  • Propose a novel DL-based framework for fault detection in maritime PdM.
  • Develop a scalable, cost-efficient software solution for the entire DL model lifecycle.

Main Methods:

  • Utilized Graph Attention Networks (GATs) for spatio-temporal feature extraction from sensor time-series data.
  • Implemented a feature-wise scoring mechanism for explainable predictions.
  • Developed a custom evaluation metric prioritizing accuracy and timeliness.

Main Results:

  • Demonstrated framework effectiveness on electrical, bearing, and water circulation datasets.
  • Achieved accurate and timely fault detection for PdM.

Conclusions:

  • The proposed DL framework offers a robust solution for PdM in maritime operations.
  • The framework is scalable, cost-efficient, and provides explainable fault detection.