Please wait while the transcript is being prepared...
0:04
The case study here is about
European energy
spares dashboard.
I know it might be probably
a little bit confusing
title for the slide.
But actually it's all about
bringing the combination of
core technology components like
advanced analytics with
AI-driven forecasting,
and inventory optimization
and cost reduction.
The main challenge
was to streamline
the complex maintenance,
repair, and operations,
or as we call it MRO processing.
That is mainly having
that ability to diverse
energy infrastructure from
different maintenance, repair,
and the full operation
in terms of including
the power plant indicators
and different installations,
for example, distributed
solar installations,
and also combining with
different energy sources
like the wind farms.
Now, here all of these
different assets,
the downtime from these assets
directly impacts
the grid stability.
A couple of years ago,
there was an event
that had a full
disruption in Spain,
Portugal, and parts of
the south of France
that connected with this.
1:36
Basically, where the
global logistic components
and these more
advanced dashboards,
where they will
be very effective
is to bring the
core technology and
the AI-driven
forecasting in order to
integrate the data
from different ERPs,
from different enterprise
resource planning systems,
and more asset
management systems
into a single
Cloud-based dashboard.
That was exactly the
case study that several
different improvements in
several different areas,
the processes were able to
be more efficient
in terms of having
these machine learning models to
analyze decades of
historical data,
including failure rates,
operational stress levels,
and external factors like
the weather patterns
and spikes in demand in order
to predict future needs.
Here, one of the KPI that was
extremely important part of
this case study was
the forecast accuracy.
Here, for the critical
high-cost components,
the demand forecast accuracy
that was measured by
the mean absolute
percentage error was
improved from an average
of 65% to over 90%.
That was massive. Only
having that ability to have
an increase in terms of
the forecast accuracy
from 65% to over 90%
was a massive improvement of
the operational excellence.
