The Study of Mixed Fuzzy CBR Technique and Using in Valve System Intelligent Design System

摘要

In this paper, we propose a hybrid decision model using case-based reasoning augmented the fuzzy logic and k nearest neighbor (k-NN) methods for aided design engine. The mixed fuzzy k-NN (MFKNN) CBR scheme which has trapezoidal, linear, negative linear, Triangular and Gaussian fuzzy operator is designed to compute memberships of engine and to provide a more flexible and practical mechanism for acquiring and reusing the expert system's decision knowledge. These methods were implemented in the database application and expert system following the example of valve system. To get the designed case, the retrieved results were compared and analyzed by mixed fuzzy k-NN algorithm or k-NN algorithm in the CBR database. It proves the validity of mixed fuzzy k-NN algorithm and CBR design system is used successfully in engine design process.