An ADRC Parameters Self-Tuning Control Strategy of Tension System Based on RBF Neural Network  

作　　者：Shanhui Liu Haodi Ding Ziyu Wang Li’e Ma Zheng Li 

机构地区：[1]Faculty of Printing,Packaging Engineering and Digital Media Technology,Xi’an University of Technology,Xi’an,710048,China [2]Shaanxi Beiren Printing Machinery Co.,Ltd.,Weinan,714000,China

出　　处：《Journal of Renewable Materials》2023年第4期1991-2014,共24页可再生材料杂志（英文）

基　　金：supported by the National Key Research and Development Program of China(Grant No.2019YFB1707200);the Key Research and Development Program of Shaanxi Province(Grant No.2020ZDLGY14-06);the Technology Innovation Leading Program of Shaanxi Province(Grant No.2020QFY03-03).

摘　　要：High precision control of substrate tension is the premise and guarantee for producing high-quality products in roll-to-roll precision coating machine.However,the complex relationships in tension system make the problems of decoupling control difficult to be solved,which has limited the improvement of tension control accuracy for the coating machine.Therefore,an ADRC parameters self-tuning decoupling strategy based on RBF neural network is proposed to improve the control accuracy of tension system in this paper.Firstly,a global coupling nonlinear model of the tension system is established according to the composition of the coating machine,and the global coupling model is linearized based on the first-order Taylor formula.Secondly,according to the linear model of the tension system,a parameters self-tuning decoupling algorithm of the tension system is proposed by integrating feedforward control,ADRC and RBF.Finally,the simulation results show that the proposed tension control strategy has good decoupling control performance and effectively improves the tension control accuracy for the coating machine.

关 键 词：Coating machine tension system decoupling control ADRC RBF 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]