AUGUST 7, 2019

Continuous condition monitoring pays off at a large power utility


A large power utility in Hawaii was looking for more frequent condition monitoring on their Balance of Plant (BOP) generation assets. The company operates several combined cycle natural gas fired power plants.


They had experienced significant equipment failures that occurred between their scheduled quarterly walkaround condition monitoring routes.

They decided to trial Petasense technology on 8-10 assets, including a critical Boiler Feed Pump (BFP), motors, several condensate pumps, heat drip pumps and auxiliary cooling water pumps, and half-a-dozen forced draft fans. They installed twenty triaxial battery powered vibration sensors (Motes) on these machines, as well as WiFi connectivity. Installation was complete in a day and they began tracking vibration using the web-based ARO Cloud software. The technicians and the reliability engineers also downloaded an iOS app to access the asset data anywhere, anytime.


Within a few days, the reliability engineers started to see the Asset Health score deteriorate and overall vibration increasing on the Boiler Feed Pump Motor.

The Asset Health Score (AHS) is generated by machine learning in real-time and trended for each individual asset [screenshot from the Petasense ARO Software]

On further analysis of the RMS trend and the spectra on the software, they were able to detect abnormal peaks and gradually increasing vibration levels. A defect was quickly detected, and analysis of the vibration and OSIsoft PI data indicated high axial vibration levels that coincided with the pump startup. Further analysis of PI data showed an unusual startup temperature trend that would rise to a peak and then settle down at a lower level.

RMS trend (average vibration) for the boiler feed pump motor, showing vibration spikes in the axial direction [screenshot from the Petasense ARO Software]

Other bearings showed a rapid rise on startup, then a gradual increase up to normal operating temperature. Manual vibration data collection during a pump start confirmed that there was impacting in the motor during the start in the axial direction, and it was noted that the outboard bearing sight glass indicator was fouled and the oil level could not be confirmed.

A recommendation was made to Operations to leave this pump running and cycle a redundant pump to minimize starts on the motor. The monitoring frequency was modified to once per hour to ensure that any changes in vibration would be detected. Oil analysis confirmed the defect, showing an increase in tin and copper as well as particle counts.

The unit entered a planned Maintenance Outage and it was discovered that the shaft journal shoulder was rubbing the outboard bearing face. When the coupling spacer was removed, they found that the pump side coupling hub had moved on the shaft, which had caused damage to the bearing face. The clearance between the hub and shaft was much higher than ideal, and a work order was written to replace the hub at the next opportunity. Post-repair check showed a normal bearing temperature rise at startup, without impacting evident in the vibration signature.

Early-stage damage shown on the pump-side coupling hub, which experienced excessive shaft clearance.

In this case, the motor would have failed before condition monitoring data was collected again, and the Motes were able to prevent unplanned downtime and provide peace of mind, knowing that they would detect earliest changes by monitoring every hour. The combination of the Asset Health score with the detailed vibration analysis capabilities showed a quick Return on Investment from implementing wireless Predictive Maintenance for this customer.