Hydrocarbon Engineering, March 2021 Issue
While most refineries have access to more data now than they previously have, many still have a difficult time making smart, data-driven reliability decisions because of a lack of tools and resources needed to collect, organize, and analyze the massive amount of data. Pinnacle’s Research and Development (R&D) team completed a study that compared a data-driven approach to current industry standard practices when modeling degradation on a reformer unit. The results of the study showed that the data-driven, machine learning model was able to more accurately predict degradation rates for the reformer unit.
Read our article in Hydrocarbon Engineering to read the complete study.