Modelling and FDI of dynamic discrete time systems using a MLP with a new sigmoidal activation function

Skoundrianos, EN; Tzafestas, SG

dc.contributor.author	Skoundrianos, EN	en
dc.contributor.author	Tzafestas, SG	en
dc.date.accessioned	2014-03-01T01:54:28Z
dc.date.available	2014-03-01T01:54:28Z
dc.date.issued	2005	en
dc.identifier.issn	09210296	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/27399
dc.subject	Fault detection and identification	en
dc.subject	Multi-layer perceptron	en
dc.subject	Sigmoidal activation functions	en
dc.subject	System modelling	en
dc.subject	Three tank system	en
dc.subject.other	Benchmarking	en
dc.subject.other	Computer simulation	en
dc.subject.other	Identification (control systems)	en
dc.subject.other	Mathematical models	en
dc.subject.other	Multilayer neural networks	en
dc.subject.other	Fault detection and identification	en
dc.subject.other	Sigmoidal activation functions	en
dc.subject.other	System modeling	en
dc.subject.other	Three tank system	en
dc.subject.other	Discrete time control systems	en
dc.title	Modelling and FDI of dynamic discrete time systems using a MLP with a new sigmoidal activation function	en
heal.type	journalArticle	en
heal.identifier.primary	10.1023/B:JINT.0000049175.78893.2f	en
heal.identifier.secondary	http://dx.doi.org/10.1023/B:JINT.0000049175.78893.2f	en
heal.publicationDate	2005	en
heal.abstract	In this paper we investigate the use of the multi-layer perceptron (MLP) for system modelling. A new sigmoidal activation function is introduced and the study is focused at the utilization of this function on a MLP that performs modelling of dynamic, discrete time systems. The role of the activation function in the training process is investigated analytically, and it is proven that the shape of the activation function and it's derivative can affect the training outcome. The method, is simulated at a well known benchmark, namely the three tank system, and is incorporated in a Fault Detection and Identification (FDI) method, also applied and simulated at the three tank system. Finally, a comparison is made with an approach that utilizes local model neural networks for system modeling. © 2004 Kluwer Academic Publishers.	en
heal.journalName	Journal of Intelligent and Robotic Systems: Theory and Applications	en
dc.identifier.doi	10.1023/B:JINT.0000049175.78893.2f	en
dc.identifier.volume	41	en
dc.identifier.issue	1	en
dc.identifier.spage	19	en
dc.identifier.epage	36	en