Web tension control of multispan roll-to-roll system by artificial neural networks for printed electronics

The mass production of printed electronic devices can be achieved by roll-to-roll system that requires highly regulated web tension. This highly regulated tension is required to minimize printing register error and maintain proper roughness and thickness of the printed patterns. The roll-to-roll system has a continuous changing roll diameter and a strong coupling exists between the spans. The roll-to-roll system is a multi-input-multi-output, time variant, and nonlinear system. The conventional proportional–integral–derivative control, used in industry, is not able to cope with roll-to-roll system for printed electronics. In this study, multi-input-single-output decentralized control scheme is used for control of a multispan roll-to-roll system by applying regularized variable learning rate backpropagating artificial neural networks. Additional inputs from coupled spans are given to regularized variable learning rate backpropagating artificial neural network control to decouple the two spans. Experimental results show that the self-learning algorithm offers a solution to decouple speed and tension in a multispan roll-to-roll system.