Supervised Learning-Based Fault Classification in Industrial Rotating Equipment Using Multi-Sensor Data
The reliable operation of rotating machinery is critical in industrial production, necessitating advanced fault diagnosis and maintenance strategies to ensure operational availability. This study employs supervised machine learning algorithms to apply multi-label classification for fault detection i...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/13/7580 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The reliable operation of rotating machinery is critical in industrial production, necessitating advanced fault diagnosis and maintenance strategies to ensure operational availability. This study employs supervised machine learning algorithms to apply multi-label classification for fault detection in rotating machinery, utilizing a real dataset from multi-sensor systems installed on a suction fan in a typical manufacturing industry. The presented system focuses on multi-modal data analysis, such as vibration analysis, temperature monitoring, and ultrasound, for more effective fault diagnosis. The performance of general machine learning algorithms such as kNN, SVM, RF, and some boosting techniques was evaluated, and it was shown that the Random Forest achieved the best classification accuracy. Feature importance analysis has revealed how specific domain characteristics, such as vibration velocity and ultrasound levels, contribute significantly to performance and enabled the detection of multiple faults simultaneously. The results demonstrate the machine learning model’s ability to retrieve valuable information from multi-sensor data integration, improving predictive maintenance strategies. The presented study contributes a practical framework in intelligent fault diagnosis as it presents an example of a real-world implementation while enabling future improvements in industrial condition-based maintenance systems. |
|---|---|
| ISSN: | 2076-3417 |