Designing a Multivariate Belt Conveyor Idler Stall Detection and Identification System with Scalability Analysis
2024

Belt Conveyor Idler Fault Detection System

Sample size: 30 publication 10 minutes Evidence: moderate

Author Information

Author(s): Shin Kyeong Su, Nam Younho, Suh Young-Joo

Primary Institution: Pohang University of Science and Technology

Hypothesis

Can a multivariate deep learning model effectively detect and identify stalled idlers in belt conveyor systems?

Conclusion

The proposed system can accurately detect and locate stalled idlers, but careful attention to network and energy efficiency is necessary.

Supporting Evidence

  • The system can handle a few sensor failures without significant accuracy loss.
  • Energy budgets must be carefully managed to prevent rapid battery drain.
  • Data reduction techniques can enhance scalability and efficiency.

Takeaway

This study shows how to use sensors to find problems with conveyor belts, which helps prevent big breakdowns.

Methodology

The study used accelerometers and microphones to collect data, which was then analyzed using a deep learning model to detect stalled idlers.

Limitations

The system's performance may degrade over time due to environmental changes and sensor aging.

Digital Object Identifier (DOI)

10.3390/s24247989

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication