Hydrocarbon Processing - February 2021 - 33

Digital Transformation
have been deployed across various industries to enable customers to maximize
long-term production, optimize maintenance spend and improve reliability-as
shown in the following examples:
1. Identification, categorization,
summary and reporting of
production losses
Challenge: Process
manufacturers need to track and
categorize performance losses
to identify bad actors, justify
improvement projects, and
perform historical and global
benchmarking. Production
loss accounting for process
manufacturing is a tedious
activity that can cost days of work
for process engineers. It requires
identifying losses, performing
root cause investigations, and
documenting the events leading
up to the loss. To make this
information available to all
interested personnel, it needs
to be easily aggregated into
reports that convey overall
equipment effectiveness and
identify unreliable equipment.
Effective use of this data can
inform decision making on capital
project spending to remove
process bottlenecks and upgrade
unreliable equipment, with the
end goal of minimizing downtime,
maximizing production rates
and optimizing maintenance.
This categorization is hard to do
retroactively, and most accurate
performance loss coding is done
either programmatically or by
frontline personnel at the time
of, or shortly after, a performance
loss event.
Solution: Digital toolsa are used
to identify performance losses
by comparing an operation to
ideal situations and creating
conditions when the operation
is constrained compared to
target. Losses are categorized
using specific conditions, where
events can be placed in the
correct categorical buckets, either
manually or logically, based on
configured thresholds. Summary
visualizations are created in the
application to represent the losses
both graphically and tabularly.

These summary visualizations
are compiled into an organizerb,
where configurable live or
scheduled date ranges are used
to create automatically generated
periodic reports, complete
with collaboration and sharing
capabilities (FIG. 1).
Result: Automatically generated
monthly reports can save
1 d/mos-5 d/mos of valuable
process engineering time. This is
time that engineers can get back
to work on improvement projects
and other value-added activities.
Easily exportable historical
loss data enables engineers
to spend more time adding
value to improvement projects
and less time developing
cost justifications.
2. Production run length
optimization
Challenge: Many process
manufacturing units hit process
throughput constraints over the
course of a run, resulting in the
degradation of production rates
over time. These constraints
are often reversible, but at the
cost of shutting down to clean/
maintain equipment. Sometimes,
the decision to shut down and
clean equipment-regaining
the throughput rate upon
startup-enables a unit to meet
its production goals sooner.
This type of planned downtime
also reduces maintenance
spend, as opposed to spending
time reacting to equipment
failure. Meeting targets sooner
translates into more production
and increased profits over the
long term. Developing solutions
to these types of optimization
problems typically requires
complex calculus, along with
advanced modeling packages and
programming experience.
Solution: A calculation enginec
was used to calculate the number
of shutdowns that would
minimize the total time required
to produce a given order size.
After determining the optimal
number of shutdown/run cycles,
engineers were able to determine
the run length between

shutdowns and to create a golden
profile of these run cycles. The
forecasted profile was then used
to compare against the actual
production rate to understand
where the projected end-of-run
date stood compared to the
best-case order fulfillment date
(FIG. 2).
Result: A sold-out production
unit had been looking at ways
to increase capacity to meet
demand. By implementing this
proactive downtime strategy, they
were able to meet supply chain
targets on average 11% sooner
over the course of the year. This
allowed them to creep production
volumes for multiple products
by a proportional amount, thus
growing sales and market share.
Takeaway. Reporting, complex calculations, modeling and other tasks required
for analysis of time series process data
have traditionally been performed using spreadsheets. As data volumes grow,
along with pressures to increase personnel productivity, new solutions are needed to deal with these and other issues.
Advanced analytics applications that
are specifically designed to deal with
time-series process data provide a solution for large data volumes. As these use
cases demonstrate, utilizing the right tool
for the job saves hours or days of process
engineer time, freeing these valuable individuals to work on higher-value activities
that will optimize production, increase
reliability and optimize maintenance.
NOTES
Seeq Workbench
b
Seeq Organizer Topic
c
Seeq Formula
a

ALLISON BUENEMANN is a Senior
Analytics Engineer for Seeq Corp.
She has a process engineering
background, and spent her
early career with ExxonMobil,
working in petrochemical
and polymers manufacturing.
Ms. Buenemann has spent much of her time
completing improvement projects to debottleneck
constrained unit operations and making operational
decisions with the goal of maximizing production.
In her current role, she draws on that manufacturing
experience to provide advanced analytics solutions
to customers in all process industry verticals.
She earned a BS degree in chemical engineering
from Purdue University in Indiana, and an MBA
degree from Louisiana State University.
Hydrocarbon Processing | FEBRUARY 2021 33

Hydrocarbon Processing - February 2021

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