An introduction to the use of neural networks in control systems (Q4790551)

From MaRDI portal

!

This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:

scientific article; zbMATH DE number 1860829
Language Label Description Also known as
default for all languages
No label defined
    English
    An introduction to the use of neural networks in control systems
    scientific article; zbMATH DE number 1860829

      Statements

      An introduction to the use of neural networks in control systems (English)
      0 references
      0 references
      0 references
      0 references
      28 January 2003
      0 references
      nonlinear design
      0 references
      neural networks
      0 references
      model predictive control
      0 references
      model reference adaptive control
      0 references
      feedback linearization
      0 references
      multilayer perceptron
      0 references
      There have been many successful attempts to use neural networks (NN), especially in nonlinear control systems, during the last years. The paper is a tutorial on a brief introduction to the multilayer perceptrons type NNs and their application in selected control systems. Namely, three control architectures are presented: Model predictive control, NARMA-2 control as a variation of the feedback linearization controller, and model reference adaptive control. These controllers demonstrate the variety of ways in which multilayer perceptron NNs can be used as basic building blocks. The practical implementation of these controllers is demonstrated on three applications: a continuous stirred tank reactor, a robot arm and a magnetic levitation system. The paper is written in a good pedagogical style and is nicely readable. References are representative, and a list of more than ten books on the subject matter, i.e., NNs for control, is collected up to date. There is also a website of the first author from where the simulations described in the paper can be reproduced with files that can be downloaded, namely ``http://hagan.ecen.ceat.okstate.edu/mhagan''.
      0 references

      Identifiers

      0 references
      0 references
      0 references
      0 references
      0 references
      0 references
      0 references
      0 references