自适应神经模糊推理系统（ANFIS）及其仿真

摘要

A nonlinear example was studied,through the study of ANFIS,and corresponding fuzzy model was established.Some simulation experiments were carded on.Direct effect of adaptive network based fuzzy inference systems （ANFIS）about training errors,the number of membership functions and ANFIS output is researched by ANFIS of MATLAB,which achieves good results. The simulation results show that ANFIS is very effective to identify the nonlinear system and its accuracy is very high.%以一个非线性模型为研究对象，通过对自适应神经模糊推理系统（ANFIS）建模机理的研究建立了非线性实例模糊模型，借助MATLAB中ANFIS的功能讨论隶属度函数的数目、ANFIS输出、训练误差等对自适应神经模糊推理系统（ANFIS）的影响，取得了良好的效果。结果表明利用ANFIS进行非线性系统建模和辨识是可行的，其辩识精度很高。