ANFIS建模的人工免疫聚类算法应用研究

App lication research on artificia l imm une clustering a lgorithm of ANF IS m odeling

结合锌钡白干燥煅烧生产过程的建模问题,针对ANFIS存在的网络易陷入局部极小点缺陷,提出了一种基于人工免疫聚类的ANFIS建模算法.该算法通过免疫网络对其抗体及记忆数据集逐代克隆、变异及抑制操作,提取有用的模糊规则数目,避免ANFIS训练陷入局部极小点的可能性.从理论机理及仿真研究上分析免疫聚类对ANFIS网络建模性能的作用,取得了良好的辨识效果.

ANFIS is easy to fall into local minima. To solve these problems, this paper proposes a new kind of artificial immune clustering algorithm for modeling of ANFIS. In this algorithm, the immune network does cloning, mutation and suppression actions to antibodies and memory data sets, extracts useful fuzzy rules from them and avoids training possibilities of ANFIS to local minimal ports. The paper applies this modeling algorithm into some Lithopone calcination process and analyzes its performance. Good modeling results are obtained.