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 Videos

Learning to Monitor Machine Health with Convolutional Bi-Directional LSTM Networks.

Rui Zhao1,2, Ruqiang Yan3, Jinjiang Wang4

  • 1School of Instrument Science and Engineering, Southeast University, Nanjing 210009, China. ekzmao@ntu.edu.sg.

Sensors (Basel, Switzerland)
|February 2, 2017
PubMed
Summary

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

Fault Diagnosis Method for Reciprocating Compressors Based on Spatio-Temporal Feature Fusion.

Sensors (Basel, Switzerland)·2026
Same author

Dual Regulation of Crystallization Behavior and Hole Transport Capability Enables Efficient Pure-Red Tin-Based Perovskite Light-Emitting Diodes.

ACS applied materials & interfaces·2026
Same author

Neural Network Circuit for Operant Conditioning with Blocking and Overshadowing Effects Based on DNA Strand Displacement.

ACS synthetic biology·2025
Same author

A dual PO group additive and anti-solvent synergistic strategy enables efficient and stable quasi-2D red perovskite LEDs.

Nanoscale·2025
Same author

Minimizing Buried Interface Energy Losses via Urea Phosphate Derivatives Enable High-Efficiency Carbon-Based Mesoscopic Perovskite Solar Cells.

Small (Weinheim an der Bergstrasse, Germany)·2025
Same author

Efficient and stable blue perovskite light-emitting diodes enabled by the synergistic incorporation of dual additives.

Nanoscale·2025
Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026
Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026
Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026
Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026
Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026
Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026
See all related articles
This summary is machine-generated.

This study introduces a Convolutional Bi-directional Long Short-Term Memory (CBLSTM) network for machine health monitoring. The CBLSTM effectively predicts tool wear from raw sensory data, outperforming existing methods.

Area of Science:

  • Manufacturing Engineering
  • Artificial Intelligence
  • Machine Learning

Background:

  • Machine health monitoring is crucial in modern manufacturing.
  • Data-driven approaches are increasingly popular but struggle with raw sensor data challenges like noise and irregular sampling.
  • Previous methods relied on manual feature engineering, requiring significant expertise and labor.

Purpose of the Study:

  • To develop an effective deep learning model for machine health monitoring using raw sensor data.
  • To address limitations of traditional feature extraction methods.
  • To predict tool wear accurately in real-life manufacturing scenarios.

Main Methods:

  • A novel Convolutional Bi-directional Long Short-Term Memory (CBLSTM) network was designed.
Keywords:
bi-directional long-short term memory networkconvolutional neural networkmachine health monitoringrecurrent neural networktool wear prediction

Related Experiment Videos

  • Convolutional Neural Networks (CNN) were used for robust local feature extraction.
  • Bi-directional Long Short-Term Memory (LSTM) networks encoded temporal dependencies from past and future contexts.
  • Stacked fully-connected and linear regression layers predicted the target tool wear value.

    • Main Results:

    • The proposed CBLSTM model successfully predicted actual tool wear using raw sensory data from a real-life test.
    • Experimental results demonstrated superior performance compared to several state-of-the-art baseline methods.
    • The model effectively handles noisy, variable-length, and irregularly sampled sequential data.

    Conclusions:

    • The CBLSTM model offers a powerful, data-driven solution for machine health monitoring in manufacturing.
    • Deep learning, specifically CBLSTM, redefines representation learning from raw sensor data, overcoming previous limitations.
    • This approach reduces reliance on manual feature engineering and expert knowledge.