Optimized blend quality returns $120 k/month in expected value

Case Study:

Client Profile

International refinery blending multiple feedstocks of fuel oil.

Project Information

Client Type

Refinery

Products Used

Machine Learning

Geography 

International

International refinery that blends fuel oil from multiple input feedstocks that desires high prediction accuracy for density, sulphur, viscosity, flash point, and p-value. There is incomplete feedstock data due to process uncertainty and measurement error.

Problem

Problem

International refinery that blends fuel oil from multiple input feedstocks that desires high prediction accuracy for density, sulphur, viscosity, flash point, and p-value. There is incomplete feedstock data due to process uncertainty and measurement error. 

Solution

Validere’s data scientists produced various machine learning models which delivers real-time estimates of previously unavailable data. Providing the ability to predict final blend quality and integrate the information across multiple client systems.
Device Frame

Results

Validere’s predictive machine uncovered $120k /month in total expected value, and 40-65 monthly hours of client team hours saved (Process engineering & optimization technical team).

+$120 k/month

Total Expected Value

Learn how Validere can transform your business.

Client Success Stories