Motor fault diagnosis based on multisensor-driven visual information fusion
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.This study introduces an advanced motor fault diagnosis framework using motor current and electromagnetic signals. The method achieves over 99.95% accuracy in identifying 8 fault types, offering robust and cost-effective industrial solutions.
Area Of Science
- Electrical Engineering
- Artificial Intelligence
- Signal Processing
Background
- Accurate motor fault diagnosis is crucial for industrial systems.
- Existing methods may lack robustness or require high costs.
- Need for enhanced signal analysis for reliable fault detection.
Purpose Of The Study
- To propose a novel fault diagnosis framework for industrial motors.
- To improve the accuracy and robustness of motor fault detection.
- To enable low-cost and high-speed motor fault diagnosis.
Main Methods
- Utilizing motor current and electromagnetic signals.
- Constructing signals into symmetric point mode (SDP) images.
- Employing a self-attention-enhanced capsule network for feature extraction.
- Implementing a multi-channel image fusion method.
Main Results
- The framework accurately identifies 8 types of motor faults under various loads.
- Achieved a fault diagnosis rate as high as 99.95%.
- Demonstrated superior robustness and effectiveness compared to single-signal models.
Conclusions
- The developed framework provides accurate and reliable motor fault diagnosis.
- The approach is beneficial for low-cost, high-speed industrial applications.
- Multi-sensor signal learning enhances diagnostic performance significantly.
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.