Hydrocarbon Processing - April 2021 - 35

Clean Fuels
variability and anomalies. They are difficult to scale, and struggle to address the
anomalies of physical assets that have
variability in vintage, makes, models
and levels of instrumentation. Furthermore, real-time operational data and asset metadata (i.e., static information like
equipment model and location) typically reside as tags in control systems, as
well as in other databases and platforms,
with accessibility issues and lack of naming standards limiting access to critical
data that could potentially be leveraged
to gain insights.
A key capability of the operational
digital twin is operational data management that creates a system of record for
operational data. The operational digital
twin is created by the SMEs over time
in an evolutionary way by first creating
smart asset digital templates that consist
of asset categories, attributes, calculations, event frames and notifications.
Attributes are grouped in categories for
providing ease of navigation and enabling the drag-and-drop configuration
of smart display templates. These attributes consist of data references to realtime data sources like DCS, SCADA,
programmable logic controllers (PLCs)
and other systems, as well as linked
tables into engineering data, the MMS
and tabular correlations like the HTHA
example. The digital twin provides configurable, no-code calculations and complex expressions by using one or more of
the more than 110 time-based functions,
such as the function library in Excel.
The smart asset template attributes
are placeholders to enable the actual
references and link tables when the templates are applied to an actual asset. The
smart assets are combined to form a base
asset hierarchy that can be used to create
relative asset hierarchies for context and
ease of navigation. Another key capability of smart asset templates is the ability
to have base and relative templates with
inheritance to allow for the anomalies
commonly found in asset classes.
The digital operational infrastructurea can enable asset anomaly detection
by allowing the SME to create or modify
anomaly expressions and then to test the
expressions by backcasting (i.e., running
the expression back into the operational
history). Once satisfied with the expression, the SME can then forward-cast this
modified expression or event detection

algorithm to other assets that utilize the
same digital twin template. This powerful capability enables continuous improvement of calculations, expressions
and event analytics over time, as well as
comparison of similar expression results,
KPIs or events as part of the diagnostic
process. FIG. 7 is an illustration of an asset hierarchy associated with a no-code
digital twin.
The no-code digital twin can include
operational metadata, engineering data
and MMS metadata to create a pump
curve and overlay with real-time pump
performance (FIG. 8). Actual pump performance can be viewed over time to see
historical performance and, for future references, be based on other forecasted information. This is also an example of how
the output of calculations and expressions can be historized to enable their use
in other calculations and analytics.

Consolidating the concepts, capabilities and applications, FIG. 9 illustrates
how smart asset templates are leveraged
to create a digital replica of a physical
renewable diesel facility and to form
the foundation for a portfolio of dashboards, KPIs and advanced decision
support capabilities.
A 'layers of analytics' strategy for renewable diesel facilities. Terms such as
advanced analytics, machine learning, big
data and artificial intelligence (AI) appear pervasively in marketing literature,
but can lead to confusion, failed projects
and significant lost opportunity costs.
The most successful operators achieve
value from analytics by first defining an
analytics framework, along with the types
of analytics required, and then selecting
fit-for-purpose technologies. They use a
" layers of analytics " strategy, which considers incremental cost vs. incremental

FIG. 7. Operational data management in a no-code operational digital twin.

FIG. 8. Example of an operational digital twin and integrated data references used in analytics
and visualization.
Hydrocarbon Processing | APRIL 2021

Hydrocarbon Processing - April 2021

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