摘要
针对 MIMO复杂过程提出一种通过实验数据获取模糊系统模型的方法 ,即将每一维输入变量的论域进行等间隔分割后确定出模糊规则的前件参数和规则总数 ,再由一种调整算法通过对实验数据的学习得到模糊规则的后件参数。理论分析说明这种模糊规则后件参数学习算法是收敛的、所建模糊模型能够以要求的精度逼近已知的实验数据。
A method is presented for obtaining a fuzzy model for a complex MIMO process using experiment data. The discourse domain of each input variable is divided equally to determine the premise parameters and the total number of fuzzy rules. The consequent parameters of the fuzzy rules are then obtained by a learning algorithm. The learning algorithm and the characteristics of the fuzzy rules model which can approximate the experiment data are shown to converge to any arbitrary accuracy by the theoretical analysis. The effectiveness of the fuzzy modeling method and the generalization ability of the fuzzy rules model are also demonstrated by a simulation example.
出处
《清华大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2001年第1期89-91,共3页
Journal of Tsinghua University(Science and Technology)
基金
国家自然科学基金资助项目!(6 96 85 0 0 2 )
内蒙古自然科学基金资助项目!(95 -0 3-4 0 )
