Bumi Datamining is the exclusive partner of VROC: a Software as a Service (SaaS) Automated Machine Learning (AutoML) platform, specifically designed and built for Industrial Big Data. VROC is built to seamlessly integrate with your existing infrastructure and used by your existing team to quickly build, train, and maintain models of your asset without programming or coding experience.
Offshore platform losing $100m+ due to re-occurring compressor failure
Standard reliability analysis took 4000 man-hours to identify root cause with little confidence in plan
Solution
VROC validated the failure root causes 2000x faster than subject matter experts, and identified additional factors
USD12 MILLION
SAVINGS IN 4-MONTHS
USD5 MILLION
ENVIRONMENTAL SAVINGS
2,000X
FASTER
FPSO Produced Water and Water Injection Pump Reliability
Challenge
A newly commissioned FPSO with over 250,000 sensors, too much data for reliability engineers to understand using existing techniques
Significant risk of unplanned downtime for critical assets
Solution
VROC monitored the critical pumps and identified degradation in performance and mechanical seals three days earlier than reliability engineers
Pump duties were changed and faulty pumps repaired without resulting in catastrophic failure or downtime
USD2 MILLION
SAVINGS IN 3-MONTHS
20%
MAINTENANCE SAVINGS
3 DAYS
EARLIER
Drill Rig Reliability
Challenge
Longer wells being drilled from aging drill rigs
High risk of Top Drive, Mud Pump, and Generator equipment failures while drilling
Solution
Install wireless IoT sensors on critical equipment to monitor them in real time
Use AI to identify unusual or undesirable operating conditions and alert operators before a failure occurs allowing them to take pro-active actions
USD65 MILLION
potential savings from avoiding failed drill hole
REAL TIME
dashboards and alerts
2,000X
FASTER
AI Identified Sand Events from Subsea Wells
Challenge
Complex interactions between subsea wells and topside processing causing unpredictable sand events
Engineers unsure of the risk factors causing sand events, or how much sand was entering topside vessels
Solution
VROC AI processed historical data to learn the leading indicators for sand events and the expected sand volume
Future sand events can be reduced by identifying the risk factors and likelihood of them occurring
Sand jetting of vessels can be optimized by knowing how much sand has entered topside vessels
USD1 MILLION
maintenance savings per
year
OVER 75%
OPTIMISED WELLS
600
extra tanker exports per year
Global Mineral Processing Refinery
Challenge
Premature filter clogging, resulting in costly and frequent shutdowns for past 20yrs
Solution
VROC ingested 12 months of process and equipment data – 44 billion data points
VROC identified the root causes of the issue which included equipment and processes in other areas of the plant.
VROC able to predict filter failures allowing operators to take steps to avoid them completely in future
USD1.2 MILLION
savings annually
1,7000
sensors
2,000X
FASTER
Global Port Operator
Challenge
Excessive maintenance was performed to increase reliability of ageing equipment, resulting in higher maintenance costs and a large spare parts inventory maintenance
Solution
VROC predicts failures allowing maintenance to be planned and performed to avoid unplanned downtime
Maintenance costs target savings of 20%
Spares inventory target saving reduction of 50%
VROC Optimize able to inform strategic asset management decisions