The mechanism and application of hybrid reasoning technology based on case and rule

A hybrid reasoning technology based on CBR(case-based reasoning) and RBR(rule-based reasoning) is put forward to the case-design of product conceptual design.CBR is a priority to search reasoning result by matching cases.It turns to the general RBR to amend the design for the similarity below standard.Due to the accuracy and efficiency of case retrieval in CBR,the paper adopts the rough set theory to process the existing case base and then finds the true weight of the feature attributes in order to improve the accuracy of case retrieval.The hybrid clustering algorithm that combines with hierarchical clustering and K-means clustering is used to form index in order to improve the efficiency of case retrieval.The feasibility and effectiveness of the proposed method are also verified by a case of motorcycle product design.