层流冷却过程中参数的模糊辨识方法  

Adaptive Parameter Identification Method in Laminar Cooling Process

作　　者：张晨缘 付晓薇[1,2,3] 李曦 ZHANG Chen-yuan;FU Xiao-wei;LI Xi(College of Computer Science and Technology,Wuhan University of Science and Technology,Wuhan Hubei430065,China;Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System,Wuhan 430065,China;State Key Laboratory of Materials Processing and Die&Mould Technology,Huazhong University of Science and Technology,Wuhan Hubei 430074,China;School of Artificial Intelligence and Automation Huazhong University of Science and Technology,Wuhan Hubei 430074,China)

机构地区：[1]武汉科技大学计算机科学与技术学院,湖北武汉430065 [2]智能信息处理与实时工业系统湖北省重点实验室,湖北武汉430065 [3]华中科技大学材料成形与模具技术国家重点实验室,湖北武汉430074 [4]华中科技大学人工智能与自动化学院,湖北武汉430074

出　　处：《计算机仿真》2022年第2期226-230,共5页Computer Simulation

基　　金：国家自然科学基金(61873323);材料成形与模具技术国家重点实验室开放课题研究基金(.P2018-016);湖北省自然科学基金(2017CFB506,2016CFA037);武汉市科技计划项目(2018010401011292);武汉科技大学国防预研基金项目(GF201912);智能信息处理与实时工业系统湖北省重点实验室开放课题项目(znxx2018ZD01)。

摘　　要：为了解决轧后温度控制中准确率和效率不足的问题,搭建了热轧带钢层流冷却动态模型,提出利用TS模糊模型对水冷换热系数进行建模。首先基于某热轧厂的工业实时数据,建立了层流冷却水冷换热系数的数据库。由于在TS模糊模型中,模糊C-均值聚类算法对初始聚类中心存在依赖性,使用人工蜂群模糊C-均值聚类算法计算隶属度函数和聚类中心,并使用卡尔曼滤波方法求解后件参数。通过结合辨识模型的特点,对机理模型进行优化。将得到的水冷换热系数,运用于某层流冷却生产模型中,可以有效提高控制精度,具有在实时工业上的应用前景。In order to solve the problem of insufficient accuracy and efficiency in temperature control after rolling, a dynamic model of laminar cooling of hot rolled strip was established, and a TS fuzzy model was proposed to model the water cooling heat transfer coefficient. Firstly, based on the real-time industrial data of a hot rolling mill, a database of water cooling heat transfer coefficients of laminar cooling was established. Because of the dependence of the Fuzzy C-Means clustering(FCM) algorithm on the initial clustering center in the TS fuzzy model, we used theArtificial Bee Colony(ABC) algorithm with fuzzy C-mean algorithm to calculate the degree of membership function and clustering center, and used the Kalman Filter(KF) method to solve the latter parameters. The mechanism model was optimized by combining the characteristics of the identification model. Applying the obtained water cooling heat transfer coefficient to a laminar cooling production model can effectively improve the control accuracy and has the prospect of real-time industrial application.

关 键 词：层流冷却 模型优化 模糊模型 人工蜂群算法 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]