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

Mechanical Efficiency of Real Machines01:14

Mechanical Efficiency of Real Machines

1.2K
The mechanical efficiency of a machine is a fundamental concept that describes how effectively a machine can convert input work into output work. According to this concept, the efficiency of a machine is equal to the ratio of the output work to the input work. An ideal machine, meaning a machine that has no energy losses, has an efficiency of one. This implies that the input work and the output work are equal.
However, in reality, no machine can be truly ideal, and all of them experience some...
1.2K
Application of Linearization and Approximation01:29

Application of Linearization and Approximation

50
A drone flying through complex terrain often relies on more than one sensing method to estimate small changes in altitude. Along with direct measurements, air pressure provides a useful indirect indicator of vertical movement. Atmospheric pressure decreases as altitude increases, and this relationship is commonly described using an exponential model. Although accurate, converting pressure measurements into altitude values requires calculations that are too complex to perform repeatedly during...
50

You might also read

Related Articles

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

Sort by
Same author

Bio-Inspired Deep Learning for Parkinson's Disease Detection: A Comparative Study Based on Vocal Biomarkers and Archimedean Spiral Analysis.

Biomimetics (Basel, Switzerland)·2026
Same author

Multi-Task and Federated Learning for Breast and Lung Cancer Screening and Diagnosis: A Survey and Future Research Directions.

Journal of imaging·2026
Same author

System for the Acquisition and Monitoring of Energy Consumption in the Context of Industry 4.0.

Sensors (Basel, Switzerland)·2024
Same author

A Method for Assessing the Reliability of the Pepper Robot in Handling Office Documents: A Case Study.

Biomimetics (Basel, Switzerland)·2024
Same author

Multi-Instance Classification of Breast Tumor Ultrasound Images Using Convolutional Neural Networks and Transfer Learning.

Bioengineering (Basel, Switzerland)·2023
Same author

Autonomous Robots for Services-State of the Art, Challenges, and Research Areas.

Sensors (Basel, Switzerland)·2023

Related Experiment Video

Updated: Jan 16, 2026

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

2.1K

An Explainable Deep Learning-Based Predictive Maintenance Solution for Air Compressor Condition Monitoring.

Alexandru Ciobotaru1, Cosmina Corches1, Dan Gota1

  • 1Automation Department, Faculty of Automation and Computer Science, Technical University of Cluj-Napoca, 400114 Cluj-Napoca, Romania.

Sensors (Basel, Switzerland)
|September 27, 2025
PubMed
Summary

Predictive maintenance (PdM) using a hybrid deep neural network (DNN) and support vector machine (SVM) model accurately predicts air compressor failures. Explainable AI (XAI) enhances the trustworthiness of these AI-driven maintenance predictions for critical infrastructure.

Keywords:
LIMEPDPSHAPSVM air compressorcondition monitoringdeep learningpredictive maintenance

Related Experiment Videos

Last Updated: Jan 16, 2026

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

2.1K

Area of Science:

  • * Industrial Engineering and Operations Research
  • * Artificial Intelligence and Machine Learning
  • * Reliability Engineering

Background:

  • * Air compressors are critical components in sectors like healthcare, manufacturing, and automotive, where failures can lead to significant disruptions and safety concerns.
  • * Predictive maintenance (PdM) is essential for enhancing the reliability of industrial equipment by detecting potential failures before they occur.
  • * Current PdM approaches require robust models capable of analyzing sensor data for early fault detection.

Purpose of the Study:

  • * To develop and evaluate a hybrid deep neural network (DNN) and support vector machine (SVM) model for predictive maintenance of air compressor components.
  • * To compare the performance of the hybrid model against standalone DNN and SVM models across various hardware platforms.
  • * To assess the impact of explainable AI (XAI) methods on the transparency and interpretability of the PdM system.

Main Methods:

  • * A hybrid DNN-SVM model was designed for condition monitoring and fault prediction of air compressor parts (exhaust valve, bearings, water pump, radiator).
  • * Models were trained and validated on NVIDIA T4 GPU, Raspberry Pi 4 Model B, and NVIDIA Jetson Nano, measuring latency, energy consumption, and CO2 emissions.
  • * Shapley Additive Explanations (SHAP), Local Interpretable Model-Agnostic Explanations (LIME), and Partial Dependence Plots (PDP) were used for model interpretability.

Main Results:

  • * The hybrid DNN-SVM model achieved high average performance metrics: 98.71% accuracy, 99.25% precision, 98.78% recall, and 99.01% F1-score across all tested devices.
  • * Standalone DNN and SVM models showed lower average performance, with F1-scores of 89.37% and 91.62%, respectively.
  • * The integration of XAI methods improved the transparency and trustworthiness of the predictive maintenance outcomes.

Conclusions:

  • * The hybrid DNN-SVM model offers a highly accurate and reliable solution for air compressor predictive maintenance.
  • * The study demonstrates the feasibility of deploying advanced AI-driven PdM solutions on edge computing devices.
  • * Explainable AI is crucial for building trust and facilitating informed decision-making in AI-powered maintenance systems.