Hydrocarbon Processing - April 2021 - 34

Clean Fuels
information. The operational
data infrastructurea and associated
smart asset templates are leveraged
to provide context and validated
data sets to the models. Optimum
targets and forecasts are outputs of
the models that are put back into
the operational data infrastructure
as " future data. " This information
is used to perform plan vs. actual
analytics, and to enable proactive,
data-based decision support,
including key information such
as lost margin opportunities, the
asset heath of PTUs and RDUs,
and other intelligence (FIG. 5).
Approach 2: A new grassroots renewable diesel facility. Many non-pe-

troleum refining companies are choosing

to design, build and operate new renewable diesel facilities that provide greater
flexibility to optimize the entire facility,
including feedstock sources and necessary purification in a PTU; the design and
catalyst selection in the RDU; the design
of the required infrastructure, including
utilities, hydrogen sources, blending and
logistics; and waste disposal.
The operational challenges, which are
fewer because of the flexibility afforded by
a grassroots design and build, are still present, and the mitigation opportunities from
the use of an operational data infrastructure remain applicable. The operational
data infrastructurea can be configured to
address the challenges and opportunities
of a grassroots design and build. One key
advantage of leveraging an operational
data infrastructure experienced by many

FIG. 5. Example of deep integration between the operational data infrastructure and modeling
software.4

FIG. 6. A critical operations integration, applications and analytics infrastructure.

APRIL 2021 | HydrocarbonProcessing.com

HPI companies is the ability to accelerate
startup, improve warranty validation, and
reduce the number of applications and solutions by more than 50%.5
Creating the smart renewable facility with an operational data infrastructure. A real-time operational infrastructurea is an agnostic, open, scalable and
reliable technology specifically designed
for critical operations to deliver operational data in a reliable way to stakeholders and applications. The infrastructure
must enable self-service analytics, deliver
all required context for operational intelligence, and have the following capabilities (FIG. 6):
* Secure integration of timeseries operational data from
the distributed control system
(DCS), supervisory control and
data acquisition (SCADA), and
Industrial Internet of Things
(IIoT) systems
* Abstraction of diverse tag and asset
names into a standard company
lexicon and asset hierarchy
* Integration of metadata, including
engineering data and information
from the MMS (FIG. 2)
* Normalization of units of measure,
time zones and asset descriptions
* Configuration of traditional
operational applications,
such as energy management,
environmental compliance and
KPI-driven dashboards
* Use of a " layers of analytics "
framework and strategy to provide
the analytics foundation via
configurable descriptive, diagnostic
and simple predictive analytics.
No-code operational digital twinsb
configured and supported by SMEs. A
digital twin is a replica of a physical asset (such as a heat exchanger, pump or
compressor) comprising attributes, calculations, KPIs, empirical correlations
and models of varying complexity. Contrary to the hype, digital twins have been
around since the 1960s. However, today's
operationally focused digital twins are
dramatically more robust and sophisticated in their ease of use, approach and
capability to develop, evolve and leverage
in a renewable diesel plant.
Most digital twins require IT, data scientists, machine learning, model integration and coding. They also have a limited
ability to deal with data volume, velocity,

http://www.HydrocarbonProcessing.com

Hydrocarbon Processing - April 2021

Table of Contents for the Digital Edition of Hydrocarbon Processing - April 2021