模糊专家系统AEGFES中基于状态空间正交划分的模式匹配算法

A Pattern Matching Algorithm Based on State Space Orthogonal Division in AEGFES

针对产生式专家系统中当规则数和事实数较大时,推理所产生的组合爆炸问题,提出了一种基于状态空间正交划分的模式匹配算法。 这里,状态空间是事实集合, 事实是术语、关系和术语值的三元组。 根据术语在规则中的不同作用, 首先将状态空间正交划分为输入子空间, 中间子空间和输出子空间。 然后, 基于状态空间正交划分, 提出了产生式模糊推理的模式匹配算法。 并将该算法运用于铝电解槽模糊专家系统AEGFES。试验表明该算法可显著提高模糊推理的匹配速度, 特别是可减少推理轮数, 和第2轮以后的匹配次数。

In this paper, we put forward fuzzy expert system AEGFES (Aluminium Electro-Groove Fuzzy Expert System)s pattern matching algorithm based on state space orthogonal division which can promote the reasoning speed ,the ESs resoning speed is very slow when the rules and facts number is very large.The running result of the AEGFES has proved that our algorithms promotion to the reasoning efficiency is very clear.