Web Processing Control using Backstepping and RBF Neural Networks

Web processing systems are very common in industry, however, controlling them is difficult because of their nature such as multi-input multi-output, time variance, and nonlinearity. In this paper, modeling and controlling of the multi-span roll to roll system, an example of a web processing system, are investigated. The general model of multi-span roll to roll system is developed based on Hooke’s law, Coulomb law, and the law of conservation of mass. From the obtained web dynamics, a backstepping based controller with Neural RBF for web velocity and tension regulation is developed. The Radial Basis Function network is used to estimate the wind and unwind roll inertia variations. Simulation results show the effectiveness of the proposed approach.