Smart Sensor-Based Monitoring Technology for Machinery Fault Detection

Area of Science:

• Mechanical Engineering
• Condition Monitoring
• Signal Processing

Background:

• Rolling element bearings are crucial for rotary machine shaft support.
• Bearing defects are a primary cause of machine performance issues.
• Reliable condition monitoring is essential for industrial machinery to prevent failures and reduce costs.

Purpose of the Study:

• To develop a smart monitoring system for real-time bearing fault detection and diagnostics.
• To create a wireless data acquisition (DAQ) system for vibration signal collection.
• To propose a modified variational mode decomposition (MVMD) technique for enhanced fault analysis.

Main Methods:

• Development of a smart sensor-based data acquisition (DAQ) system for wireless vibration data.
• Application of a modified variational mode decomposition (MVMD) technique for nonstationary signal analysis.
• Utilizing correlation kurtosis for IMF selection, analytical signal construction, and envelope spectrum analysis for feature identification and fault prediction.

Main Results:

• Successful development of a wireless DAQ system for vibration signal collection.
• Implementation of MVMD for effective decomposition and analysis of bearing vibration signals.
• Experimental validation demonstrating the capability to identify bearing fault features and predict faults.

Conclusions:

• The developed smart sensor DAQ system and MVMD technique are effective for real-time bearing fault detection.
• The proposed method provides an early warning system for bearing defects.
• This approach can significantly contribute to preventing machine performance degradation and reducing maintenance expenses.