Direct Learning for Parameter-Varying Feedforward Control
A Neural-Network Approach
Johan Kon (Eindhoven University of Technology)
Jeroen Van De Wijdeven (ASML)
Dennis Bruijnen (Philips Research)
Roland Tóth (Eindhoven University of Technology, Institute for Computer Science and Control (SZTAKI))
Marcel Heertjes (ASML, Eindhoven University of Technology)
Tom Oomen (Eindhoven University of Technology, TU Delft - Team Jan-Willem van Wingerden)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
The performance of a feedforward controller is primarily determined by the extent to which it can capture the relevant dynamics of a system. The aim of this paper is to develop an input-output linear parameter-varying (LPV) feedforward parameterization and a corresponding data-driven estimation method in which the dependency of the coefficients on the scheduling signal are learned by a neural network. The use of a neural network enables the parameterization to compensate a wide class of constant relative degree LPV systems. Efficient optimization of the neural-network-based controller is achieved through a Levenberg-Marquardt approach with analytic gradients and a pseudolinear approach generalizing Sanathanan-Koerner to the LPV case. The performance of the developed feedforward learning method is validated in a simulation study of an LPV system showing excellent performance.