A Combined Decoupling Controller for Register System of Roll-To-Roll Gravure Printing Machines

For the nonlinear and strongly disturbing register system of the unit gravure printing machines, a self-tuning method of PID parameters based on RBF neural network is proposed to solve the problem of insufficient dynamic margin of the PID controller in the printing process. Firstly, a nonlinear mathematical model of the global register system is established based on the structure of the gravure printing equipment system and register principle. Then, a PID parameter self-tuning controller integrating RBF neural network is designed for register mathematical model. Finally, the simulations are carried out to verify the control performance of the proposed method in terms of robustness, decoupling performance, and interference resistance. The results show that, compared with the traditional PID controller, the designed controller can better suppress the influence of disturbances and has a higher register accuracy, while solving the problem of controller performance degradation under different working conditions.