Premium
NONLINEAR NETWORK STRUCTURES FOR FEEDBACK CONTROL
Author(s) -
Lewis F.L.
Publication year - 1999
Publication title -
asian journal of control
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.769
H-Index - 53
eISSN - 1934-6093
pISSN - 1561-8625
DOI - 10.1111/j.1934-6093.1999.tb00021.x
Subject(s) - control theory (sociology) , backstepping , nonlinear system , controller (irrigation) , bounded function , artificial neural network , nonlinear control , stability (learning theory) , mathematics , computer science , network topology , control (management) , adaptive control , artificial intelligence , mathematical analysis , physics , quantum mechanics , machine learning , agronomy , biology , operating system
A framework is given for controller design using Nonlinear Network Structures, which include both neural networks and fuzzy logic systems. These structures possess a universal approximation property that allows them to be used in feedback control of unknown systems without requirements for linearity in the system parameters or finding a regression matrix. Nonlinear nets can be linear or nonlinear in the tunable weight parameters. In the latter case weight tuning algorithms are not straightforward to obtain. Feedback control topologies and weight tuning algorithms are given here that guarantee closed‐loop stability and bounded weights. Extensions are discussed to force control, backstepping control, and output feedback control, where dynamic nonlinear nets are required.