Ontologies for Process Control
Early in 2007, Dr. Mark Fox and Prof. Michael Grüninger initiated a project with
the manufacturing software company SAP.
This project is primarily concerned with the design of an ontology
to support reasoning about process control and material flow within an
often distributed discrete manufacturing chain and the ability to map
from/to the data model used in SAP discrete manufacturing applications.
Typical problems in this domain involve the recording of process constraints
associated with a particular resource as it passes through the set of
activities performed within the manufacturing chain.
In addition to the specification of a process plan for the resource
(which specifies the partially ordered set of activities performed with
the resource), they also want to specify additional constraints on the
occurrences of activities (such as temporal and quality constraints).
For any given resource and time point, the ontology should support queries
related to explanation and prediction. With respect to explanation,
we would like to determine which activities that require the resource
have already occurred and provide the rationale for why and in which
context these activities occurred. The set of explanations provide a
complete trace of all manufacturing activities. With respect to prediction,
we want to identify the subsequent activities that may possibly occur
so that the complete set of constraints will be satisfied. The set of
predictions will be used to dynamically determine the routing of the
resource and prevent the occurrences any activities that are inconsistent
with the set of process constraints.
<<back to projects
|
