17-03-2014, 12:42 PM
Abstract— An adaptive strategy for knowledge-based control
of sophisticated plants is considered. The domain knowledge is
structured using a set of ontologies – factual ontology and
functional ontologies (for tasks, problem solving methods, way
to realize the methods, activities – adaptive control,
monitoring). The active part of the control system is
accomplished using a multiagent system. An Ant Colony
Optimization is proposed for fulfilling different optimization
procedures. A brief description is given for the structure, the
functions and the processes of the developed multiface control
system. The software realization is OWL-based for the
ontologies and JADE-based for the intelligent agents. An
example for adaptive control of a non-square (SITO) plant is
considered.
Keywords- adaptive systems, ant colony optimization,
automatic control, multiagent system, ontology
I. INTRODUCTION
In common cases of industrial plant control the
environment is distributed, heterogeneous and it’s composed
from different system types. Such kinds of systems are
needed for more flexible and dynamic control structure in a
way to achieve the optimal system control. For this kind of
systems the usage of knowledge based control system with
adaptation of knowledge is very effective. The combination
of knowledge based system, which is presented from
ontologies, and the usage of pro-active intelligent modules,
presented by agent system, gives an optimal control [6, 7, 8].
In common cases the system behavior is dynamic with a
lot off changes: a different operational condition, changes
into system constrains, changes into SITO (Single Input Two
Output) Plant parameters, different technological regimes,
presence of big disturbances and etc.
For such kind of systems is suitable to be control via
Multiagent-Ontological System, which gives a number of
advantages [6, 7, 8]:
• The system is knowledge based. It uses ontologies
and agents in order to take into account previous
knowledge received by experts in a form of heuristic
rules, rules extraction from data, case-based
reasoning etc., which leads to fast system adaptation
according current situation conditions.
• The knowledge representation in this investigation
an ontology system is created as a set of domain
ontologies, corresponding to the environment, plant,
agents, and constraints.
• The proposed control system is intelligent in the
wide established sense of this notion being able to
the next functionality: it can react adequately at
unforeseen disturbances; it can use the results of online
inter agent’s negotiation; it could be both
reactive and proactive.
of sophisticated plants is considered. The domain knowledge is
structured using a set of ontologies – factual ontology and
functional ontologies (for tasks, problem solving methods, way
to realize the methods, activities – adaptive control,
monitoring). The active part of the control system is
accomplished using a multiagent system. An Ant Colony
Optimization is proposed for fulfilling different optimization
procedures. A brief description is given for the structure, the
functions and the processes of the developed multiface control
system. The software realization is OWL-based for the
ontologies and JADE-based for the intelligent agents. An
example for adaptive control of a non-square (SITO) plant is
considered.
Keywords- adaptive systems, ant colony optimization,
automatic control, multiagent system, ontology
I. INTRODUCTION
In common cases of industrial plant control the
environment is distributed, heterogeneous and it’s composed
from different system types. Such kinds of systems are
needed for more flexible and dynamic control structure in a
way to achieve the optimal system control. For this kind of
systems the usage of knowledge based control system with
adaptation of knowledge is very effective. The combination
of knowledge based system, which is presented from
ontologies, and the usage of pro-active intelligent modules,
presented by agent system, gives an optimal control [6, 7, 8].
In common cases the system behavior is dynamic with a
lot off changes: a different operational condition, changes
into system constrains, changes into SITO (Single Input Two
Output) Plant parameters, different technological regimes,
presence of big disturbances and etc.
For such kind of systems is suitable to be control via
Multiagent-Ontological System, which gives a number of
advantages [6, 7, 8]:
• The system is knowledge based. It uses ontologies
and agents in order to take into account previous
knowledge received by experts in a form of heuristic
rules, rules extraction from data, case-based
reasoning etc., which leads to fast system adaptation
according current situation conditions.
• The knowledge representation in this investigation
an ontology system is created as a set of domain
ontologies, corresponding to the environment, plant,
agents, and constraints.
• The proposed control system is intelligent in the
wide established sense of this notion being able to
the next functionality: it can react adequately at
unforeseen disturbances; it can use the results of online
inter agent’s negotiation; it could be both
reactive and proactive.