模糊推理的变权综合算法及其构造的模糊系统响应能力分析

Variable Weighted Synthesis Method for Fuzzy Inference and Analysis of Response Ability of the Constructed Fuzzy Systems

将变权综合原理应用于模糊推理,提出一种新的模糊推理算法-变权综合推理算法,并给出利用模糊蕴涵算子确定规则变权的方法。证明了由一些正常蕴涵算子如Lukasiewicz蕴涵、Goguen蕴涵、Godel蕴涵、Dubois-Prade蕴涵等确定的变权综合算法是相容的。进一步分析了该变权综合算法构造的模糊系统的响应能力,结果表明:基于这些正常蕴涵算子的变权综合算法构造的模糊系统具有泛逼近性。

The principle of variable weighted synthesis is applied to fuzzy inference and a new fuzzy inference method called variable weighted synthesis inference method is introduced, and a construction approach of variable weights of rules by fuzzy implication operators is proposed. It is proved that the inference algorithms based on some normal implication operators are consistent, and the fuzzy systems constructed by these algorithms are universal approximators.