✦ LIBER ✦

Neural networks and dynamical systems

✍ Scribed by Kumpati S. Narendra; Kannan Parthasarathy

Publisher: Elsevier Science
Year: 1992
Tongue: English
Weight: 965 KB
Volume: 6
Category: Article
ISSN: 0888-613X
DOI: 10.1016/0888-613x(92)90014-q

No coin nor oath required. For personal study only.

✦ Synopsis

Models for the identification and control of nonlinear dynamical systems using neural networks were introduced by Narendra and Parthasarathy in 1990, and methods for the adjustment of model parameters were also suggested. Simulation results of simple nonlinear systems were presented to demonstrate the feasibility of the schemes proposed. The concepts introduced at that time are investigated in this paper in greater detail. In particular, a number of questions that arise when the methods are applied to more complex systems are addressed. These include nonlinear systems of higher order as well as multivariable systems. The effect of using simpler models for both identification and control are discussed, and a new controller structure containing a linear part in addition to a multilayer neural network is introduced.

📜 SIMILAR VOLUMES

Dynamical systems produced by recurrent

Dynamical systems produced by recurrent neural networks

✍ Masahiro Kimura; Ryohei Nakano 📂 Article 📅 2000 🏛 John Wiley and Sons 🌐 English ⚖ 237 KB 👁 2 views

Concerning the learning problems of recurrent neural networks (RNNs), this paper deals with the problem of approximating a dynamical system (DS) by an RNN as one extension of the problem of approximating trajectories by an RNN. In particular, we systematically investigate how an RNN can produce a DS

Identification of linear and nonlinear d

Identification of linear and nonlinear dynamic systems using recurrent neural networks

✍ D.T. Pham; X. Liu 📂 Article 📅 1993 🏛 Elsevier Science 🌐 English ⚖ 531 KB

Dynamic Modeling of Chemical Reaction Sy

Dynamic Modeling of Chemical Reaction Systems with Neural Networks and Hybrid Models

✍ Hans-Jörg Zander; Roland Dittmeyer; Josef Wagenhuber 📂 Article 📅 1999 🏛 John Wiley and Sons 🌐 English ⚖ 211 KB 👁 2 views

Nonlinear dynamics extraction for time-d

Nonlinear dynamics extraction for time-delay systems using modular neural networks synchronization and prediction

✍ S. Ortín; J.M. Gutiérrez; L. Pesquera; H. Vasquez 📂 Article 📅 2005 🏛 Elsevier Science 🌐 English ⚖ 231 KB

Identification of power system dynamics

Identification of power system dynamics due to combined use of mathematical model and neural network

✍ Norio Takahashi; Hiromasa Takeno; Yasuharu Ohsawa 📂 Article 📅 2001 🏛 John Wiley and Sons 🌐 English ⚖ 252 KB

## Abstract In order to obtain a reliable model of power systems, identification of power system dynamics by employing a neural network is studied. A new method of combined use of a mathematical model and a neural network is proposed. The effectiveness of the proposed method is verified by applying

Fluctuation-driven learning rule for con

Fluctuation-driven learning rule for continuous-time recurrent neural networks and its application to dynamical system control

✍ Kazuhisa Watanabe; Takahiro Haba; Noboru Kudo; Takahumi Oohori 📂 Article 📅 2001 🏛 John Wiley and Sons 🌐 English ⚖ 220 KB 👁 2 views