论文信息 - On training radial basis function networks as series-parallel and parallel models for identification of nonlinear dynamic systems

On training radial basis function networks as series-parallel and parallel models for identification of nonlinear dynamic systems

Identification of linear and nonlinear dynamic systems can be performed with a series-parallel or parallel model. In this paper both approaches are compared. While many applications require the model to run in parallel to the process, usually the identification procedure is carried out with a series-parallel model. This paper shows that optimization of a series-parallel model does not necessarily lead to a good parallel model. Furthermore a decrease of the error in one configuration may result in an increase in the other.

Oliver Nelles

[1] F. Girosi,et al. Networks for approximation and learning , 1990, Proc. IEEE.

[2] Kumpati S. Narendra,et al. Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[3] John Moody,et al. Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.

[4] Rolf Isermann,et al. Identification of nonlinear dynamic systems with radial basis function networks: linear versus nonlinear optimization , 1995 .

[5] A. Ravindran,et al. Engineering Optimization: Methods and Applications , 2006 .

[6] Dimitry Gorinevsky. On the persistency of excitation in RBF network identification , 1994, Proceedings of 1994 American Control Conference - ACC '94.

[7] Rolf Isermann,et al. Identifikation dynamischer Systeme , 1988 .

[8] Rolf Isermann,et al. Identification of nonlinear dynamic systems classical methods versus radial basis function networks , 1995, Proceedings of 1995 American Control Conference - ACC'95.