摘要
利用SVD技术重构PSG模糊规则库,降低规则的数量。根据矩阵奇异值的性质,适当取舍模糊规则库后件矩阵Ω的奇异值,得到Ω的近似表示^Ω,利用^Ω重新构建规则库,新规则库的输入变量域的维数比原规则库的维数小,从而有效地降低了模糊规则数。仿真结果证明了该方法是有效的。
<Abstrcat>The method using SVD to rebuilding PSG fuzzy model is presented in this paper,in new model,the number of fuzzy rules is reduced.In terms of the property of singular values,an approximation of matrix Ω,which is conducted by consequents of fuzzy rules,is obtained by selecting proper singular values of Ω.Using the approximation of Ω,a new rule base is constructed.Generally,the dimension of imput variables in new rule base is smaller than in original one,thus,the size of rule base is reduced effectively.Finally,a numerical example with simulations is given to demonstrate the method discussed throughout this paper.
出处
《中国管理科学》
CSSCI
2005年第3期103-107,共5页
Chinese Journal of Management Science
