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 Video

Updated: Dec 3, 2025

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

855

Deep convolutional neural network based on adaptive gradient optimizer for fault detection in SCIM.

Prashant Kumar1, Ananda Shankar Hati1

  • 1Department of Mining Machinery Engineering, Indian Institute of Technology (Indian School of Mines), Dhanbad, Jharkhand, 826004, India.

ISA Transactions
|October 30, 2020
PubMed
Summary
This summary is machine-generated.

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

Residual LSTM-based short duration forecasting of polarization current for effective assessment of transformers insulation.

Scientific reports·2024
Same author

Interventions for improving indoor and outdoor air quality in and around schools.

The Science of the total environment·2022
Same author

Integrated proteomics and phosphoproteomics revealed druggable kinases in neoadjuvant chemotherapy resistant tongue cancer.

Frontiers in cell and developmental biology·2022
Same author

Morphological study of the menisci of the knee joint in human cadaver in Jharkhand population.

Journal of family medicine and primary care·2022
Same author

Addendum: Liquid biopsy and multi-analyte testing guided treatment of <i>HER2</i> positive periampullary adenocarcinoma with durable complete response after trastuzumab based therapy.

Oncotarget·2022
Same author

Role of fluorescein angiography guided laser treatment in aggressive retinopathy of prematurity.

Eye (London, England)·2022

This study introduces an adaptive gradient optimizer deep convolutional neural network (ADG-dCNN) for early fault detection in squirrel cage induction motors. The method achieves 99.70% accuracy in identifying bearing and rotor faults, reducing manual intervention.

Area of Science:

  • Mechanical Engineering
  • Artificial Intelligence
  • Signal Processing

Background:

  • Squirrel cage induction motors (SCIMs) are critical in industrial applications.
  • Downtime due to SCIM faults leads to significant economic losses.
  • Early fault detection is essential for operational efficiency and maintenance.

Purpose of the Study:

  • To develop an automated fault detection system for SCIMs.
  • To detect bearing and rotor faults using vibration data.
  • To minimize reliance on manual feature extraction and expertise.

Main Methods:

  • Utilized an adaptive gradient optimizer based deep convolutional neural network (ADG-dCNN).
  • Employed multiple MEMS accelerometers for vibration data acquisition.
Keywords:
Adaptive gradient optimizerBearing faultBroken rotor barConvolutional neural network (CNN)Squirrel cage induction motor (SCIM)

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.8K

Related Experiment Videos

Last Updated: Dec 3, 2025

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

855
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.8K
  • Implemented sensor data fusion for model training and testing.
  • Applied SHapley Additive exPlanations (SHAP) for model interpretability.

    • Main Results:

    • The ADG-dCNN model achieved an average accuracy of 99.70% in fault classification.
    • Demonstrated automatic feature extraction from vibration data, reducing human intervention.
    • Successfully detected bearing and rotor faults in SCIMs.

    Conclusions:

    • The proposed ADG-dCNN technique offers a highly accurate and automated solution for SCIM fault detection.
    • The end-to-end learning system minimizes errors associated with manual feature engineering.
    • The methodology is adaptable for fault detection in other multi-sensor machinery.