Feedforward nonlinear control using neural gas network
Summary: Nonlinear systems control is a main issue in control theory. Many developed applications suffer from a mathematical foundation not as general as the theory of linear systems. This paper proposes a control strategy of nonlinear systems with unknown dynamics by means of a set of local linear models obtained by a supervised neural gas network. The proposed approach takes advantage of the neural gas feature by which the algorithm yields a very robust clustering procedure. The direct model of the plant constitutes a piecewise linear approximation of the nonlinear system and each neuron represents a local linear model for which a linear controller is designed. The neural gas model works as an observer and a controller at the same time. A state feedback control is implemented by estimation of the state variables based on the local transfer function that was provided by the local linear model. The gradient vectors obtained by the supervised neural gas algorithm provide a robust procedure for feedforward nonlinear control, that is, supposing the inexistence of disturbances.
- An introduction to the use of neural networks in control systems
- Batch and median neural gas
- Controllability of Nonlinear Discrete-Time Systems: A Lie-Algebraic Approach
- scientific article; zbMATH DE number 2243005 (Why is no real title available?)
- Nonlinear adaptive control using neural networks and multiple models
- Recurrent neural networks for nonlinear output regulation
- Special issue: Neural network feedback control
- State feedback control of switched linear systems: an LMI approach
This page was built for publication: Feedforward nonlinear control using neural gas network
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2012775)
