Plenary
Lecture
The Role of Reinforcement Learning in Business
Integrated Manufacturing
Associate Professor Luiza Daschievici
Faculty of Engineering Braila
"Dunarea de Jos" University of Galati, ROMANIA
E-mail:
luiza.tomulescu@ugal.ro
Abstract: All over the world, companies are faced
with increasingly accelerated and unpredictably dynamic
changes. This is influenced by the scientific, technical
progress and the dynamics of customers' demands. Changes
lead to aggressive competition on a global scale, which
calls for the establishment of new balances between
economy, technology and society.
Reinforcement learning (RL) has received some attention
in recent years from researchers, because it deals with
the problem of how an autonomous manufacturing system
can learn to select proper actions for achieving its
goals through interacting with its environment. Although
there have been several successful examples
demonstrating the usefulness of RL, its application to
business integrated manufacturing has not been fully
explored yet. The interaction between the economic
environment and the manufacturing system is a major
source of knowledge about the economic environment and
the manufacturing system themselves.
The reinforcement learning, through its role, in
business integrated manufacturing, means the
manufacturing system capacity to 'learn' in permanent
interaction with the economic environment, to inform and
update the information about the auctions and to
anticipate, before deciding to conclude a contract, the
level of costs, profit and what is the best way to act.
In other words this means that the manufacturing system
'learns' what actions to take in certain situations,
based on the data supplied by the economic environment,
so that such actions increase the possibilities of
achieving the aim proposed.
The business integrated manufacturing should 'exploit'
what it already knows to obtain profit, but at the same
time it must 'explore' the possibility of finding other
suitable actions for the future. The manufacturing
system should try a variety of actions and then choose
those that seem best. This study shows the potential of
RL for application to the business integrated
manufacturing.
Brief Biography of the Speaker:
Luiza Daschievici got a Master's degree in Mechanical
Engineering in 1994.
In 2000 Luiza Daschievici got a PhD in Mechanical
Engineering ("Dunarea de Jos" University of Galati).
Since 1994, she has been an assistant, then lecturer and
associate professor at "Dunarea de Jos" University of
Galati.
Her research fields are the following: technology of the
manufacturing process; cutting process modeling;
tribology of parts machines; techniques of complex
modelling of the manufacturing systems; the reliability
of the mechanics systems.
Dr. Daschievici Luiza has participated in many research
projects organized by Romanian Ministry of Education and
Science.
She published, as author or co-author, over 80 articles
in journals and proceedings of the international
conference (Hungary, Italy, Hong Kong, Spain, Portugal,
Poland, South Africa, Ukraine, Bulgaria, Moldavia, USA).
Daschievici Luiza wrote 5 books in her research field.
She is a member of the following professional and
scientific associations: IFAC – International Federation
of Automatic Control, SAAM - South African for
Theoretical and Applied Mechanics, ARoTMM - Romanian
Association for Theory of Machines and Mechanisms, ACM-V
- Multidisciplinary Research Association of the West
Zone.
Dr. Daschievici Luiza is an expert of Romanian National
University Research Council – CNCSIS.
|