基于ACO的连铸结晶器液位控制系统设计  

Design of Continuous Casting Mould Level Control System Based on ACO

作　　者：唐立伟[1] 李权[1] 李和平[1] Tang Liwei;Li Quan;Li Heping(College of Mechanical and Electrical Engineering,Loudi Vocational and Technical College,Loudi,Hunan 417000,China)

机构地区：[1]娄底职业技术学院机电工程学院,湖南娄底417000

出　　处：《机电工程技术》2021年第3期158-160,共3页Mechanical & Electrical Engineering Technology

基　　金：湖南省教育厅资助科研项目(编号:19C1548)。

摘　　要：常规PID不适用于具有非线性、时变特性和耦合性强等特征的连铸机结晶器液位控制系统,为此设计一种蚁群优化BP神经网络的智能PID控制器。采用系统辩识方法确定结晶器液位控制系统的数学模型;设计了控制器的系统结构,采用蚁群算法(ACO)训练BP网络的权值,以获得全局最优PID控制参数,在Matlab中进行仿真。实践结果表明,该算法收敛速度快、无超调、稳定性好。The conventional PID controller is not suitable for the mold level control system of continuous casting machine with nonlinear,time-varying characteristics and strong coupling.An intelligent PID controller based on ant colony optimization BP neural network was designed.The mathematical model of mold level control system was determined by system identification method;the system structure of the controller was designed,and the weights of BP network were trained by ant colony algorithm(ACO)to obtain the global optimal PID control parameters,the simulation was carried out in Matlab.The results show that the algorithm has fast convergence speed,no overshoot and good stability.

关 键 词：结晶器液位控制 蚁群算法 智能PID控制 MATLAB仿真 

分 类 号：TP241[自动化与计算机技术—检测技术与自动化装置]