基于进化模糊系统生成可理解的知识表达

Understandable Knowledge Representation Based on Evolution Fuzzy System

讨论了最简约模糊划分、模糊划分的完备-清晰性、模糊规则的完备性和一致性,并根据这些指标构造适应度函数,使进化模糊系统不仅响应性能良好,而且可获得物理意义明显的结构和参数,从而使其表达的知识更易理解。应用Box-Jenk ins煤气炉数据的仿真实验表明了该方法的有效性。

The minimal fuzzy partition, completeness and distinguishability of fuzzy partition, and consistency of rule are discussed. Fitness function is built based on these indexes. The proposed techniques are demonstrated by means of the benchmark example： for identification of the well-known Box-Jenkins gas furnace. The obtained result is compared with results from the literature.