Paper Technology International 2020 - Journal - Page 14

PAPERTECHNOLOGYINTERNATIONAL
Can AI run a mill better than humans?
Many companies are developing data lake-based solutions,
where they collect data from automation, mill execution and ERP
systems. Data maintenance and modelling, however, need to be
solved before the data becomes practically useful. Obstacles include
unharmonized master data or missing domain knowledge. How to
cope with vast amounts of process data from multiple automation
systems is another issue.
Analytics scalability needs looking at. What works on one
machine may not work on another. Therefore, models need to be
self-learning, using long-term historical data to learn correctly. If
the model, for example, does not know the quality of raw materials
used, self-learning algorithms are missing essential information
leading to wrong decisions.
While analytics services progress as IT initiatives from the
top down, automation suppliers are approaching the issue from the
bottom up. They typically focus on a specific machine or machines
and usually do not cover the complete production line.
Quality controllers today are not designed to optimize both
quality and cost, as they do not have the information to do it. This is
where major cost savings potential is hiding: optimizers on various
levels feed their information to automation to enable holistically
optimized production.
Figure 2: Mills need to move away from running production
business processes almost fully based on human decisionmaking. TIPS AI - Artificial Intelligence (AI) and Machine
Learning (ML) help mills to improve efficiency and quality
while enabling lower costs.
As artificial intelligence (AI) and machine learning (ML) go
forward and start to provide reliable results, the next step is to hook
algorithms into active process control. This requires standard API
interfaces and services across multivendor environments.
AI and ML for efficiency, quality, and lower cost
Embedding AI and ML into manufacturing execution systems
allows mills to improve three important aspects of meeting customer
demand – operational efficiency, promised quality and lower cost.
The market demands constantly faster customer response,
production profitability requires increasing flexibility, together with
flexibility and efficient resource usage.
12
Manufacturing Execution Systems (MES) play a central
role. To reduce costs, leading producers are going towards more
automated mills, balancing between highly educated operators
responsible for everything versus automated routines with operators
only focusing on more demanding tasks.
Managing order intake (combined with automatic pricing,
credit check, logistics and production planning) helps secure a
customer’s business; further automation in roll production increases
efficiency; traceability in converting improves runnability and
printability by providing feedback to roll production.
The pulp & paper industry needs to renew and look for major
savings potential. This will happen by automating mainly manual
business processes in the offices and enabling operator mobility at
shop-floor level. AI and ML are the drivers of the change.
Future AI-based support for operators will drive production
consistently in an optimal way, which calls for much deeper
integration between automation and business systems. Mills need to
move away from running production business processes almost fully
based on human decision-making.
Data is the foundation of the autonomous mill and business
operations
We live in a data-rich world with new technology, security
and privacy concerns, increased demands,
and broadened connectivity. This creates
new challenges to follow global trends
and to make the best use of technology
innovations and making more value out of
the data.
Today’s and tomorrow’s trend
is to minimize cost, maximize operation
efficiency, increase flexibility, and improve
customer services.
Tomorrow’s systems must be able
to assume a more prominent role and
more responsibility in decision-making.
MES works at the crossroads between
information systems, machines, and
humans, while simultaneously having a
central position in the architecture. It must
be tightly connected with the environment
and must optimize user interaction.
Contrary to what we might think,
however, the operator will still have an important role to play.
The MES of tomorrow will help and “drive” people in their
daily tasks. Human effort is re-focusing on value-added tasks:
•
Anticipating deviations
•
Eliminating time loss
•
Reducing errors
This allows more time for operational managers to work
on optimizing the value chain. Operators will be tightly integrated
with all types of systems and partners (automation, mobile devices,
customers, suppliers) that support business process improvement
and enhance user experience by delivering real-time, optimized
information.
It is still not possible to automate everything but when
manual operations are needed, MES informs the operator with
meaningful information about concerns and needed operations.

Paperturn flipbook