摘要： 提出了一种递推窗口式多层构造简化模糊推论模型。在该模糊模型中，因各层的分割数相异，而使得该模糊规则具有不同特性。在其模糊分割数较多的层上，可以获得高辩识精度的模糊规则，而在分割数较少的层上，模糊规则的生成变得简单易行。该文通过对两个非线性函数的辩识实验，验证了多层构造简化模糊推论模型有效性。

关键词: 模糊推论模型, 多层构造, 辨识精度

Abstract: This paper proposes a multi-layer structural fuzzy model using iterative transfer window. In this fuzzy model, the fuzzy rules are generated on every fuzzy division layer with different fuzzy partitions from other layers. On the fuzzy division layer with many partitions, the fuzzy rules have high reasoning accuracy, and on that with a few partitions, the generation of the fuzzy rules is easy. Through identification experiments of two nonlinear functions,the paper shows the fuzzy rules generated by the proposed method have high identification accuracy even for those problems.

中图分类号: 

• TP181