FNN模型参考自适应控制在轧机液压弯辊系统中的应用  

Fuzzy Neural Network Model Reference Adaptive Control Method for the Hydraulic Bending Roll in the Control System of UC Rolling Mill

作　　者：陈丽[1] 李建更[1] 乔俊飞[1] 王笑波[2] 

机构地区：[1]北京工业大学电子信息与控制工程学院,北京100022 [2]宝钢技术中心自动化所,上海201900

出　　处：《计算机测量与控制》2005年第12期1396-1399,共4页Computer Measurement &Control

基　　金：国家自然科学基金与宝钢集团公司联合资助(50274003)

摘　　要：UC轧机液压弯辊系统的数学模型具有很强的时变性和不确定性,是典型的非线性过程;针对UC轧机液压弯辊系统的特性,提出模糊神经网络模型参考自适应控制策略,并将其应用到液压弯辊控制系统中;仿真结果表明,模糊神经网络模型参考自适应控制能够很好的跟踪参考模型的设定,系统的响应快。The mathematical model of hydraulic bending roll system has strong time-variant property and uncertainty in the control system of UC rolling mill. To realize accuratc control of hending of the intermediate rolls, a fuzzy neural network model reference adaptive control method is presented to control the hydraulic bending roll system in which fuzzy logic control and neural network are combined. The experimental result indicates that the control effect is excellent, namely small ultra -- regulated and good robustness, reaching the goal of the intelligence control for shape on line.

关 键 词：液压弯辊 模糊神经网络 BP网络 模型参考自适应控制 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]