摘要
在王国俊教授提出的满足还原性的单一规则的全蕴涵三I算法基础上,利用模糊集合的相似度给每条模糊推理规则赋予权重,即wi=1-S2,i■I1+S2,i∈I,其中S={max S1,S2,…,Sn}且I=i|Si=S,{1≤i≤n},使得全蕴涵三I算法在一般的模糊推理情形下也满足还原性。最后通过实例表明:用新方法推理得出的结果比文献[4]的全蕴涵三I算法的结果更具合理性。
Based on the Wang Guojun＇ s triple I method that satisfies the reductive property for single--rule fuzzy inference, by in troducing similarity measure to endow each fuzzy rule with the weight, we get a triple I method with the reductive property of general fuzzy inference, that is wi=1-S2, iI1＋S2, i∈I,wherein S=max{＆, Sz, ＂＂, ＆,} and I=（i｜Si=S, l≤i≤n}. Finally, an example：results obtained with a new method of reasoning than the literature [4] the full implication triple I method results more reasonable.
出处
《重庆师范大学学报（自然科学版）》
CAS
CSCD
北大核心
2013年第3期103-106,共4页
Journal of Chongqing Normal University:Natural Science
关键词
模糊推理
还原性
全蕴涵三I算法
相似度
fuzzy inference
reductive property
triple I method
similarity measure
