An Oil & Energy Provider in the United States. They provide equipment, oil & gas drilling, and production services.
The client was having difficulty with crippling and unnecessary maintenance costs, static thresholds in their reporting, and reactive maintenance. This resulted in considerable loss of revenue (up to $1M/month), excessive maintenance costs (up to $500k/month), and drastically decreased efficiency due to increased downtime.
Sparkhound worked with client leadership and IT teams to significantly improve the predictive equipment maintenance processes that resulted in 80 percent recovery of lost revenue and maintenance costs. The updated process included:
Updating the static thresholds to be dynamic based on the patterns of the existing telemetries
Near real-time anomaly detections allowing quicker corrective action
Establishing a classification system for events before they occur by implementing advanced Artificial Intelligence and Machine Learning models
80% recovery of lost in revenue in equipment maintenance costs
Automated actions for the business-critical equipment allowing for “self-healing” functionality
Proactive maintenance while avoiding device replacement and unnecessary penalties