ANFIS的板形控制动态影响矩阵方法  

A dynamic influence matrix method for flatness control based on adaptive-network-based fuzzy inference systems

作　　者：张秀玲[1,2] 逄宗鹏[1,2] 李少清[1,2] 张少宇[1,2] 

机构地区：[1]燕山大学电气工程学院,河北秦皇岛066004 [2]燕山大学工业计算机控制工程河北省重点实验室,河北秦皇岛066004

出　　处：《智能系统学报》2010年第4期360-365,共6页CAAI Transactions on Intelligent Systems

基　　金：国家自然科学基金资助项目(50675186)

摘　　要：针对板形控制系统的非线性和强耦合性,以及传统效应函数法和板形静态影响矩阵法的不足,通过对大量生产实测数据的计算和分析,提出了板形控制的动态影响矩阵法.通过基于减法聚类的ANFIS(自适应神经模糊推理系统)的板形动态矩阵预测模型,在线求得不断变化的影响矩阵,兼顾了板带生产的实时性与复杂性,仿真实验验证了其有效性.Flatness control systems have both strong nonlinearity and coupling. Unfortunately traditional effective function methods and the static influence matrix of flatness can not effectively solve such problems. After analysis of a large volume of production data a new method was proposed,a dynamical influence matrix method for the flatness controller. Using the predictive model of the dynamic flatness matrix,and incorporating the subtractive clustering of an adaptive neuro-fuzzy inference system （ANFIS）,the influence matrix was calculated in real time. Both the need for real-time results and the complexities of strip steel production were accommodated. Simulations confirmed the validity of the proposed method.

关 键 词：板形控制 自适应神经模糊推理系统 影响矩阵 聚类 模糊 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]