Below you can find some results of iQunet condition monitoring performed on conveyors used in the Manchester International Airport. The complete set-up and results can be found in this presentation.
A Machine Learning data model has been created for all used condition monitoring sensors (trained on the sensor data of the first 1000 measurements). The iQunet Anomaly Monitor system makes it easy to detect anomalies (measurements that differ too much from the calculated model) or anomaly trends.
Wireless vibration monitoring:
8 power cabled Vibration Sensors have been installed on motors and gearboxes driving the conveyor system to monitor the vibration on the system. The following figure shows the follow-up of a gearbox where the anomaly trends on the X and Z axis have increased over the last week.
Inspection of the sensor measurements of the past week in the Vibration Lab in the iQunet Sensor Dashboard shows that an impact has been detected on the gearbox. This is an early warning detection. The recommended actions are:
Checking the chain links,
Checking the sprocket teeth,
Checking the change after lubrication.
It is however recommended to follow up the anomaly trend graphs and the machine’s behavior to exclude teeth damage inside the gearbox.
Wireless motor current monitoring (MCSA):
12 Current Clamps and 4 corresponding iQunet Sensor Bridges (for the digitization and wireless transfer of the Current Clamp signals) have been installed on speed drives of the conveyor system to monitor the motor current. The following figure shows the follow-up of a motor where the motor current anomaly trend has increased over the last week.
Inspection of the current measurements of the past week in the Current Monitor in the iQunet Sensor Dashboard shows that a motor current harmonic has been detected. The recommended actions are:
Following up the anomaly trend over time,
Following up the detected harmonic in the frequency domain.
If the anomaly trend and/or harmonic level increases quickly, prepare to schedule a motor repair.