The use of semantic networks to adapt a design prototype for electromagnetic device optimization

The ability of case-based reasoning (CBR) systems to solve new problems mainly depends on their case adaptation knowledge and adaptation strategies. In order to improve the performance of a case-based reasoning paradigm for the creative design of electromagnetic (EM) devices, we have adopted a semantic network to organize related adaptation knowledge, and then construct a rule system as an inference engine which is based on the network. The feasibility of this approach is validated by deriving a novel design prototype from a real-world induction motor case-base with high dimensionality.