Key Techniques Research On Case-Based Reasoning For Stamp Die Design Based On Rough Set Theory

Being free from great dependence on designer's experience and being more rapid and intelligent is always the improvement trend of the die-design. How to improve the intelligent level and shorten the design period attract almost all the attentions of the researchers in the CAD (Computer Aided Die Design) area. This paper will apply CBR (Case-based Reasoning) technique based on Rough Sets Theory (RST) in the field of the Die design, so it can implement intelligentized reasoning of Die design using existed project. It should improve the design quality and efficiency, shorten the period of development and reduce the cost of die.Firstly, this paper expatiate CBR technique and RST in details. Then it discusses the mainly technique of case retrieval in current, and summarizes their advantages and disadvantages in applied areas. Secondly, on the basis of introduction of the basic principle of cased-based design methods of stamping die, the knowledge representation of case system is presented in this paper. And then an approach of reducing the feature attributes and calculating the feature attributes weighting is proposed based on rough set theory. i.e., the importance of the feature attributes are calculated first, and then the importance are normalized to weighting coefficients. This method can overcome the shortcoming in traditional methods which depend on subjective experience excessively. Thirdly, in the foundation of the analysis to the practical die design processing and the intelligent CAD system, it builds a functional model based on IDEF0's Die CAD system. Therefore, this paper brings forward and builds a Die CAD system framework based on CBR-RST. The same time, the related-database system of die criterion cases based on C/S pattern is realized.