Neural networks for function approximation in nonlinear control

Dennis J. Linse, Robert F. Stengel

Research output: Contribution to journalConference article

7 Scopus citations

Abstract

Two neural network architectures are compared with a classical spline interpolation technique for the approximation of functions useful in a nonlinear control system. A standard back-propagation feedforward neural network and a cerebellar model articulation controller (CMAC) neural network are presented, and their results are compared with a B-spline interpolation procedure that is updated using recursive least-squares parameter identification. Each method is able to accurately represent a one-dimensional test function. Tradeoffs between size requirements, speed of operation, and speed of learning indicate that neural networks may be practical for identification and adaptation in a nonlinear control environment.

Original languageEnglish (US)
Pages (from-to)674-679
Number of pages6
JournalProceedings of the American Control Conference
StatePublished - May 1990
EventProceedings of the 1990 American Control Conference - San Diego, CA, USA
Duration: May 23 1990May 25 1990

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Neural networks for function approximation in nonlinear control'. Together they form a unique fingerprint.

Cite this