SearchPublisher and Institutes
You are here: Home :: Area NEM :: Engineering :: Automation
Stefan Jakubek, Christoph Hametner, Nikolaus Keuth, A. Voigt
New Methods for Dynamic Identification with Neuro-Fuzzy Networks
Keywords: Takagi-Sugeno Fuzzy models, nonlinear modeling, identification
This article deals with the identification of nonlinear dynamic processes with local Neuro-Fuzzy networks. These networks have the advantage that their architecture offers the possibility to incorporate in-depth process know-how into the modeling procedure. The article presents solution approaches for two major issues in dynamic identification: First, the problem of noisy input- and output data is treated, which causes biased parameters when conventional regression techniques are applied. As a possible solution, the concept of Total Least Squares is presented and adapted for application in local Neuro-Fuzzy Networks. Second, a method for the enforcement of stationary gains is presented that significantly improves the model precision during steady-state phases. Results from a practical example illustrate the applicability of both concepts.
at – Automatisierungstechnik, Oldenbourg Wissenschaftsverlag
Print ISSN: 0178-2312
Volume: 54, 10/2006
Pages: 486 - 494