Imperfect Roll Arrangement Compensation Control based on Neural Network for Web Handling Systems

Abstract

The speed and tension control problem of a web handling system is investigated in this paper. From the system equations of motion, we developed a backstepping-sliding mode control for web speed and tension regulation tasks. It is obvious that the designed control depends heavily on roll inertia information. Dissimilar to other researches that were based on the assumptions of rolls with perfect cylindrical form with the rotating shafts of the rolls considered properly aligned, the novelty of this paper is the presentation of a neural network to compensate the effects of imperfect roll arrangement. The neural network design is based on the Radial Basis Function (RBF) network estimating the uncertainty of roll inertia. The information on estimated inertia is fed into a backstepping-sliding mode controller that ensures tension and velocity tracking. The control design is presented in a systematical approach. Closed loop system stability is proven mathematically. The tracking performance is shown through several simulation scenarios.

A sliding mode controller integrated moment of inertia observer of web handling systems

“…It is more powerful and superior to PID controllers because it reduces dependence on model inaccuracies and external disturbances. So there has been much research to develop this SMC, and there are many remarkable achievements [13][14][15][16]. In [17], the authors used a SMC to bring the synchronizing error of the induction To overcome these inadequacies, the research team has developed a sliding mode controller integrated moment of inertia observer.…”

Model‐free hierarchical control with fractional‐order sliding surface for multisection web machines

“…The authors innovated a Backstepping-based Control structure incorporated with an RBF network for roll inertia change estimation. 45 An RBF Neural Network-based Backstepping Sliding Mode Control (RBFNN-BSMC) 46,47 in which changeable inertia of rolls is approximated for the adaptive ability of control system was addressed to reach tracking and flexibility goals. Also, an equivalent control architecture was suggested as in the study, 48 of which remarkable innovation is to estimate the derivative of virtual control signal such that the "explosion of terms" phenomenon is successfully eliminated.…”