Information Technology Reference
In-Depth Information
The KBES developed is capable of integrating qualitative information of the rule-base with
quantitative data of the database and the feature library. It uses forward chaining approach
for firing the rules in the rule-base and to achieve the goal. Forward chaining starts with the
data available (for example the plane of holes, size of holes, and centre-to centre distance
between holes) and uses the inference rules to extract more data until a desired goal (for
example the possibility of using multi-drill head) is reached. An inference engine searches
the inference rules until it finds one in which the “if” clause is known to be true. It then
concludes the “then” clause and adds this information to its data. It continues to do this
until a “goal” is reached. The system stores input and output information of the processed
workpieces in the database for future use. Therefore, it adds to the extent of its knowledge.
To determine the feasibility of utilization of SPM for a new workpiece, the inference engine
first searches the database to find out whether it has been processed before. If so, it uses
previously restored information. If not processed before then the inference engine searches
for similar workpieces. When a similar workpiece is found then the system provides user
with possibility of interactive modification if necessary. When a similar workpiece is not
found then it is processed by the system.
Fig. 12. Developed feature library containing 3D solid models of standardized SPM components
