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

Sequence Networks of Rotating Machines01:24

Sequence Networks of Rotating Machines

368
A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
368
Transformers in Distribution System01:27

Transformers in Distribution System

408
Transformers in distribution systems can be broadly categorized into distribution substation transformers and other distribution transformers. They are crucial for stepping down high transmission voltages to levels suitable for distribution and end-user applications.
Distribution substation transformers come in various ratings and typically use mineral oil for insulation and cooling. To prevent moisture and air from entering the oil, some transformers use an inert gas like nitrogen to fill the...
408
Linear time-invariant Systems01:23

Linear time-invariant Systems

673
A system is linear if it displays the characteristics of homogeneity and additivity, together termed the superposition property. This principle is fundamental in all linear systems. Linear time-invariant (LTI) systems include systems with linear elements and constant parameters.
The input-output behavior of an LTI system can be fully defined by its response to an impulsive excitation at its input. Once this impulse response is known, the system's reaction to any other input can be...
673

You might also read

Related Articles

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

Sort by
Same author

On a Hybrid CNN-Driven Pipeline for 3D Defect Localisation in the Inspection of EV Battery Modules.

Sensors (Basel, Switzerland)·2025
Same author

Condition Monitoring and Predictive Maintenance of Assets in Manufacturing Using LSTM-Autoencoders and Transformer Encoders.

Sensors (Basel, Switzerland)·2024
See all related articles

Related Experiment Video

Updated: Nov 18, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.5K

A Deep Learning Model for Predictive Maintenance in Cyber-Physical Production Systems Using LSTM Autoencoders.

Xanthi Bampoula1, Georgios Siaterlis1, Nikolaos Nikolakis1

  • 1Laboratory for Manufacturing Systems and Automation, Department of Mechanical Engineering and Aeronautics, University of Patras, 26504 Patras, Greece.

Sensors (Basel, Switzerland)
|February 4, 2021
PubMed
Summary

This study introduces a deep learning approach for predictive maintenance in industrial settings. It enables condition monitoring and remaining useful life estimation for cyber-physical production systems, moving beyond traditional preventive schedules.

Keywords:
Long Short-Term Memory (LSTM)artificial intelligencecyber-physical production systemsdeep learningpredictive maintenanceremaining useful life

Related Experiment Videos

Last Updated: Nov 18, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.5K

Area of Science:

  • Industrial Engineering
  • Machine Learning
  • Cyber-Physical Systems

Background:

  • Condition monitoring and machine learning can enhance maintenance in cyber-physical production systems.
  • Acquiring high-quality data for both normal and abnormal operational states non-destructively is challenging.
  • Current preventive maintenance relies on fixed schedules, not actual equipment status.

Purpose of the Study:

  • To enable a transition from preventive to predictive maintenance in cyber-physical production systems.
  • To develop a deep learning methodology for classifying machine and sensor data into condition-related labels.
  • To estimate the remaining useful life (RUL) of industrial equipment.

Main Methods:

  • Utilized a deep learning algorithm for predictive maintenance planning based on real-time operational status.
  • Employed an autoencoder-based methodology for classifying real-world machine and sensor data.
  • Implemented and tested Long Short-Term Memory (LSTM) autoencoders for RUL estimation using manufacturing data.

Main Results:

  • Successfully classified real-world machine and sensor data into condition-related labels.
  • Demonstrated the capability of LSTM autoencoders to estimate the remaining useful life of monitored equipment.
  • Validated the proposed approach in a steel industry production process use case.

Conclusions:

  • The proposed deep learning approach facilitates a shift towards predictive maintenance in industrial environments.
  • Autoencoder-based condition monitoring and RUL estimation are effective for cyber-physical production systems.
  • The methodology offers a data-driven alternative to traditional time-based preventive maintenance.