基于扩展模糊Petri网的知识推理方法研究

Knowledge Reasoning Method Based on Extended Fuzzy Petri Net

为使模糊Petri网能够描述可变模糊隶属判据下的模糊知识,利用基准变换能较好地表达模糊隶属判据可变情况的特点,基于定性映射和定性基准变换对模糊Petri网进行了扩展,给出了扩展后网模型的形式定义和基本运行机制。通过利用定性映射描述模糊产生式规则,给出了一种新的知识表示模式和推理方法,新方法有利于构建模糊Petri网基于认知的学习机制。结果显示,该网模型具有较强的知识表达能力,适用于处理认知模糊不确定性知识,其推理过程能体现某些认知特性,尤其适用于构建以定性判断为特点的智能系统。

In order to make fuzzy Petri nets have ability to describe the fuzzy knowledge under the variable fuzzy membership,taking the advantage of the characteristic that the criterion transformation can well express the variable fuzzy membership,the fuzzy Petri net was extended based on the qualitative mapping and the qualitative criterion transformation.The formal definition and the basic operation mechanism of the expanded Petri net were given.The qualitative mapping was used to describe the fuzzy production rule.A new model of knowledge representation and reasoning method was put forward.The new method is good for constructing fuzzy Petri net learning mechanism based on cognition.Results show that the network model has strong ability of knowledge representation.It is suitable for processing fuzzy uncertainty knowledge The cognitive reasoning process can reflect certain cognitive characteristics,so it is especially suitable for building the intelligent system with qualitative judgment.