Open Access

ARTICLE

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

Shanhui Liu^1,*, Haodi Ding¹, Ziyu Wang¹, Li’e Ma¹, Zheng Li²

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

* Corresponding Author: Shanhui Liu. Email:

(This article belongs to the Special Issue: Green, Recycled and Intelligent Technologies in Printing and Packaging)

Journal of Renewable Materials 2023, 11(4), 1991-2014. https://doi.org/10.32604/jrm.2022.023659

Received 07 May 2022; Accepted 26 July 2022; Issue published 01 December 2022

Abstract

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.

---

Graphic Abstract

---

Keywords

---