基于IDE-RBF-PID-PI的炉温串级控制系统的设计  

Design of Furnace Temperature Cascade Control System Based on IDE-RBF-PID-PI

作　　者：刘悦婷[1] 张燕[1] LIU Yueting;ZHANG Yan(School of Electronics and Communication Engineering,Lanzhou University of Arts and Science,Lanzhou 730000,China)

机构地区：[1]兰州文理学院电子与通信工程学院,甘肃兰州730000

出　　处：《长春师范大学学报》2025年第2期35-41,共7页Journal of Changchun Normal University

基　　金：兰州市科技计划项目“基于混合智能算法的加热炉主蒸汽温度优化控制系统研究”(2023-3-88);甘肃中振数字技术有限公司横向项目“含分布式电源的智能电网的故障诊断研究”(LWL-KJ-2024-056)。

摘　　要：针对加热炉物料出口温度大滞后的特点,提出一种改进差分进化算法的径向基神经网络的PID-PI串级控制系统,先采用IDE算法优化RBF的初始参数,再由RBF在线辨识得到梯度信息,最后根据梯度信息对PID的3个参数进行在线调整,并将3个参数应用在主控制器调整中,副控制器采用PI控制。炉温控制系统实验结果表明,与DE-RBF-PID-PI串级控制和RBF-PID-PI串级控制相比,IDE-RBF-PID-PI串级控制抗干扰性能更强、响应速度更快、稳定性更好、控制效果更优。To address the large time delay in the heating furnace outlet temperature,PID-PI cascade control based on improved differential evolution algorithm and radial basis function(RBF)neural network is proposed.First of all,the initial parameters of RBF are optimized by IDE algorithm.Then the gradient information is obtained by RBF online identification.Finally,the three parameters of PID are adjusted online according to the gradient information.The three parameters are applied to the adjustment of the main controller,and the sub controller adopts PI control.The experimental results of furnace temperature control system show that compared with DE-RBF-PID-PI cascade control and RBF-PID-PI cascade control,IDE-RBF-PID-PI cascade control has stronger anti-interference performance,faster response,better stability and better control effect.

关 键 词：改进差分进化算法 RBF径向基神经网络 串级控制 加热炉系统 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]