文章基本信息

标题：A neural network-based robust unknown input observer design: Application to wind turbine
本地全文：下载
作者：Piotr Witczak ; Krzysztof Patan ; Marcin Witczak 等
期刊名称：IFAC PapersOnLine
印刷版ISSN：2405-8963
出版年度：2015
卷号：48
期号：21
页码：263-270
DOI：10.1016/j.ifacol.2015.09.538
语种：English
出版社：Elsevier
摘要：The paper deals with the problem of robust unknown input observer design for the neural-network based models of non-linear discrete-time systems. Authors review the recent development in the area of robust observers for non-linear discrete-time systems and proposes less restrictive procedure for design the H∞ observer. The approach guaranties simultaneously the predefined disturbance attenuation level (with respect to state estimation error) and convergence of the observer. The main advantage of the design procedure is its simplicity. The paper presents an unknown input observer design that reduced to a set of linear matrix inequalities. The final part of the paper presents an illustrative example concerning wind turbine.
关键词：ObserverFault DiagnosisUnknown InputsRobustnessSystem IdentificationTakagi-Sugeno systemsArtificial Neural NetworksSector Non-linearities