基于数据驱动的多卷料张力协同控制系统  

Data-driven multi-winding tension cooperative control system

作　　者：庞浩 杜钦君[1] 徐东祥 吴育桐 马炳图 PANG Hao;DU Qin-jun;XU Dong-xiang;WU Yu-tong;MA Bing-tu(School of Electrical and Electronic Engineering,Shandong University of Technology,Zibo 255022,China;State Grid Shandong Electric Extrahigh Voltage Company,Jinan 250000,China;Zibo Product Quality Inspection Research Institute,Zibo 255022,China)

机构地区：[1]山东理工大学电气与电子工程学院,山东淄博255022 [2]国网山东超高压公司,济南250000 [3]淄博市产品质量检验研究院,山东淄博255022

出　　处：《控制与决策》2025年第3期909-917,共9页Control and Decision

基　　金：国家自然科学基金项目(62076152);山东省科技型中小企业创新能力提升项目(2022TSGC1186,2023TSGC0966).

摘　　要：三电机卷绕系统是一个强耦合非线性时变系统,存在卷轴半径、转动惯量以及摩擦系数等时变参数,导致张力协同控制精度较低.为了提高卷绕系统模型准确度,实时优化张力协同控制系统的动态性能,提出一种基于改进鲸鱼算法优化的多核最小二乘支持向量机回归(multi-kernel least squares support vector regression prediction model based on an improved whale algorithm optimization,WOA-M-LSSVR)预测模型和基于纵横交叉优化算法(crisscross optimization algorithm,CSO)优化的模型预测张力协同控制系统.根据最小二乘支持向量机回归原理建立多核LSSVR回归模型,并使用改进的自适应鲸鱼算法进行离线优化,得到系统预测模型;根据建立的预测模型,构建自适应更新的模型预测控制器,引入纵横交叉优化算法实现优化求解,最大程度避免了求解陷入局部最优的情况,提高了张力控制系统的动态性能.通过仿真和实验分析,验证了所设计的张力协同控制系统具有良好的动态性能和鲁棒性.The three-motor winding system is a strongly coupled nonlinear time-varying system with time-varying parameters such as spool radius,rotational inertia,and friction coefficient,which leads to low accuracy of tension cooperative control.To improve the accuracy of the winding system model and enhance the dynamic performance of the tension cooperative control system in real-time,we propose a multi-kernel least squares support vector regression prediction model based on an improved whale algorithm optimization and a model-predictive tension cooperative control system utilizing crisscross optimization.According to the principle of least squares support vector machine regression,a multi-kernel LSSVR regression model is established,and the improved adaptive whale algorithm is used for offline optimization to obtain the system prediction model.Employing the established prediction model,we construct an adaptive model-predictive controller.The vertical and horizontal cross-optimization algorithm is incorporated to attain the optimal solution,effectively mitigating the risk of the solution getting trapped in local optima and thereby enhancing the dynamic performance of the tension control system.Through extensive simulation and experimental analyses,it is demonstrated that the tension cooperative control system designed in this paper exhibits superior dynamic performance and robustness.

关 键 词：卷绕系统 张力控制 模型预测控制器 最小二乘支持向量机 鲸鱼算法 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]