Two turbine compressors were operating in parallel on an offshore platform. The operator wanted earlier visibility of developing
reliability and performance issues so the team could intervene before undesirable operation resulted in a shutdown.
A Time to Failure model was built using turbine compressor rotational speed as the target, trained on historical patterns of critically low
lube oil level, providing early warning on lube oil system malfunctions.
Rather than assessing speed in isolation, the model analyzed its relationship with other operating parameters. Contributor analysis
identified lube oil reservoir level as the strongest factor associated with the developing speed degradation.
Each reduction in reservoir level requiring an oil top-up corresponded with renewed model warnings — behavior that was not observed
on the parallel turbine compressor. This directed attention toward the lubrication system. The operations team subsequently rectified a
major leak by addressing the coupling cover and tightening connections, after which model warnings reduced and compressor
performance improved.
The model repeatedly identified increased risk as lube oil reservoir level fell. By analyzing the relationship between compressor
parameters, VROC highlighted lube oil level as the leading indicator of oil consumption to the developing performance issue. Following
rectification of the leak, model warnings reduced and performance improved.
Earlier visibility of performance degradation
The Time to Failure model provided warning as turbine speed moved toward the
defined undesirable operating condition of 8,000 rpm.
Faster problem isolation
Contributor analysis moved the investigation beyond the symptom of declining compressor speed and
identified lube oil reservoir level as the key parameter associated with the issue.
Targeted corrective action
The operations team rectified the coupling-cover leak and tightened associated connections. Model
warnings subsequently reduced and compressor performance improved.
VROC combines early failure prediction with contributor analysis, helping operations and reliability teams identify developing conditionsand focus investigation on the parameters most strongly associated with them.
Explore Time to Failure Prediction | Talk to Our Team
Industry: Oil and Gas
Solution: Predictive Maintenance & Reliability
Use Case: Time to Failure Prediction
Facility: Offshore Platform
Asset: Turbine Compressor
Gain real-time visibility, predict failure earlier, optimize performance, and take control of your operations with VROC’s integrated solutions.