In the global refining marketplace the single
biggest cost is the raw feedstock: crude oil. To
improve margins, increasing, the use of
'opportunity crudes' helps to lowers the cost of
the crude blend.
However, as these oils are new to the
marketplace and many refineries have never
processed them before it brings about challenges
including, lack of understanding of the quality
of the crude oil being processed (shale oils for
example can come from many thousands of wells)
and how these oils interact with the more
conventional blended crude oils.
Intertek are a Total Quality Assurance provider
to industries worldwide including the oil and
gas sector. Their Interpret software package
uses NIR Spectroscopy alongside data analysis
techniques to provide real-time prediction of
the properties of Hydrocarbon streams without
the need for time consuming lab experiments.
Enabling the end user to have a better
understanding of how their specific feedstock
will behave in their process.
This project will seek to investigate the
development and incorporation of new
state-of-art clustering and classification
algorithms into the Interpret software package,
with the objective of improving the predictive
performance of their software package, allowing
Intertek to stay at the forefront of their
competition in providing their customers with
real-time, traceable insight on crude oil