一类三层前向折线模糊神经网络的构造  

Construction of a class of three-layered feedforward polygonal fuzzy neural network

作　　者：李丹[1] 孙刚[2] 王贵君[1] 

机构地区：[1]天津师范大学数学科学学院,天津300387 [2]大连海事大学轮机工程学院,辽宁大连116026

出　　处：《东北师大学报（自然科学版）》2012年第3期55-59,共5页Journal of Northeast Normal University(Natural Science Edition)

基　　金：国家自然科学基金资助项目(60974144)

摘　　要：为克服模糊数运算的复杂性引入了折线模糊数的概念,并应用其优良性质和折线模糊值函数的表示定理,通过插值神经网络的构造方法获得了一类三层前向折线模糊神经网络,证明了该折线模糊神经网络是连续折线模糊值函数的泛逼近器.The polygonal fuzzy numbers are introduced to overcome the complexity of fuzzy numbers’ operations,and then,by means of good properties of polygonal fuzzy numbers and the representation theorem of polygonal fuzzy numbers valued functions,the three-layer polygonal fuzzy neural networks are constructed through the constructing methods of interpolation neural networks.Finally,the approximation of the class of polygonal fuzzy neural networks with respect to the continuous polygonal fuzzy valued functions is proved.

关 键 词：折线模糊数 折线模糊值函数 插值神经网络 折线模糊神经网络 泛逼近 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] O159[自动化与计算机技术—控制科学与工程]