基于智能算法的平整延伸率系统辨识与控制  

Identification and control of elongation system of skin pass mill based on intelligent algorithm

作　　者：任新意 高慧敏 黄华贵 王晓东 孙静娜 REN Xin-yi;GAO Hui-min;HUANG Hua-gui;WANG Xiao-dong;SUN Jing-na(Technology Center,Shougang Jingtang Iron and Steel Co.,Ltd,Tangshan 063200,China;National Engineering Research Center for Equipment and Technology of Cold Rolling,Yanshan University,Qinhuangdao 066004,China)

机构地区：[1]首钢京唐钢铁联合有限责任公司技术中心,河北唐山063200 [2]燕山大学国家冷轧板带装备及工艺工程技术研究中心,河北秦皇岛066004

出　　处：《重型机械》2021年第3期34-38,共5页Heavy Machinery

基　　金：国家自然科学基金(51674222,51474189)。

摘　　要：鉴于平整延伸率控制系统具有非线性、大时滞和时变性等特点,通过分析平整延伸率控制系统的机理模型,利用BP神经网络算法对模型结构参数进行系统辨识。结合生物免疫系统的调节作用和模糊推理逻辑对非线性函数的可逼近特性,将免疫反馈机理和模糊控制理论与传统PID控制结合,设计了一种模糊免疫PID控制方法,提高了平整延伸率的控制精度。仿真结果表明,该控制策略具有超调量小,响应速度快,抗干扰能力和鲁棒性强等优点,控制效果优于传统控制方法。In view of the nonlinear,time-varying and time-delay characteristics of elongation control system of skin pass mill,according to analysis of the mechanism model of elongation control system of skin pass mill,BP neural network was used to identify the structural parameters of the model.With reference to the regulating function of biological immune system and the function of fuzzy reasoning logic which can approach nonlinear function,a fuzzy immune PID control strategy was proposed to improve the elongation control accuracy of skin pass mill combining fuzzy control and immune feedback mechanism with traditional PID control.The simulation results show that the control strategy has the advantages of small overshoot,fast response,strong anti-interference ability and robustness,and the control effect is better than the traditional control method.

关 键 词：平整机 延伸率 系统辨识 神经网络 模糊免疫PID 鲁棒性 

分 类 号：TG335[金属学及工艺—金属压力加工]