粒度模糊规则建模方法研究综述

Review of the research of granular fuzzy rule-based modeling

本文旨在梳理粒度模糊规则模型中的主要研究及构建方法,并且进行系统分析与总结。粒计算是一种能模拟人类思维方式和求解复杂问题的新兴理论体系,以此为基础的粒度模型为复杂非线性系统的描述和问题求解探索了新的方向。粒度模糊规则模型将信息粒融入现有的模糊规则建模方法中,进行粒度级别的系统建模,以实现更高层次的数据分析与推理。本文简要介绍模糊聚类和模糊规则模型的基础知识;归纳了信息粒的构建方法,并讨论了相应的评估方法;总结了典型的粒度模糊规则模型的设计架构和优化方法。

The purpose of this paper is to explore the main research and construction method for granular fuzzy rule model,and make a systematic analysis and summary of it.Granular computing is an emerging theoretical system that simulates patterns of human thinking and solves complex problems,and the granular model based on it explores a new direction for the description and problem solving of complex nonlinear system.Among which the granular fuzzy rule-based model incorporates information granule into existing fuzzy rule-based modeling methods to achieve granular-level system modeling for data analysis and inference at a higher level.This paper first briefly introduces the basics of fuzzy clustering and fuzzy rule-based models,next summarizes the construction method of information granules and discusses corresponding evaluation methods.Further,the design architecture and optimization method are summarized.