Neuro-based optimal regulator for a class of system with uncertainties
暂无分享,去创建一个
This paper proposes a neuro-based optimal regulator (NBOR) for a class of system with uncertainties. In this paper, we show how the neural network output compensates the control input based on the Riccati equation and how the compensatory solution of the Riccati equation is estimated by the least-squares method. Then, the NBOR is applied to systems with uncertainties in order to illustrate its effectiveness and applicability.
[1] M. Athans,et al. Robust linear quadratic designs with real parameter uncertainty , 1994, IEEE Trans. Autom. Control..
[2] George A. Rovithakis,et al. Direct adaptive regulation of unknown nonlinear dynamical systems via dynamic neural networks , 1995, IEEE Transactions on Systems, Man, and Cybernetics.
[3] K S Narendra,et al. Control of nonlinear dynamical systems using neural networks. II. Observability, identification, and control , 1996, IEEE Trans. Neural Networks.