From neural state-space description of marine powerplants to reduced-order Volterra models

Xiros, NI; Tsourapas, VP

dc.contributor.author	Xiros, NI	en
dc.contributor.author	Tsourapas, VP	en
dc.date.accessioned	2014-03-01T02:43:20Z
dc.date.available	2014-03-01T02:43:20Z
dc.date.issued	2005	en
dc.identifier.issn	07431619	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/31342
dc.subject	Dynamic Behavior	en
dc.subject	Frequency Domain	en
dc.subject	Nonlinear Model	en
dc.subject	State Space	en
dc.subject	Steady State	en
dc.subject	Taylor Expansion	en
dc.subject	Thermodynamic Model	en
dc.subject	Input Output	en
dc.subject	Neural Network	en
dc.subject.other	Control equipment	en
dc.subject.other	Mathematical models	en
dc.subject.other	Neural networks	en
dc.subject.other	Nonlinear control systems	en
dc.subject.other	Polynomials	en
dc.subject.other	Thermodynamics	en
dc.subject.other	Input-output models	en
dc.subject.other	Marine powerplants	en
dc.subject.other	State-space description	en
dc.subject.other	Volterra expression	en
dc.subject.other	Ship propulsion	en
dc.title	From neural state-space description of marine powerplants to reduced-order Volterra models	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ACC.2005.1470266	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ACC.2005.1470266	en
heal.publicationDate	2005	en
heal.abstract	The problem of reduced nonlinear input-output models for marine propulsion powerplants is visited by starting from the neural state-space description of the system, the neural networks of which can be trained by using steady-state data of the powerplant collected either from measurements or derived by use of conventional thermodynamic models. The analysis proposed is based on the Taylor expansion of the logistic sigmoid function, appearing in the neural torque approximators of the neural plant description, yielding a finite polynomial Volterra expression, approximating the dynamic behavior of the plant with desired accuracy. The reduced nonlinear model obtains finally the form of a sum of homogenous Volterra operators, and can be used for frequency domain characterization of the system and the design of nonlinear feedforward controllers. © 2005 AACC.	en
heal.journalName	Proceedings of the American Control Conference	en
dc.identifier.doi	10.1109/ACC.2005.1470266	en
dc.identifier.volume	3	en
dc.identifier.spage	2017	en
dc.identifier.epage	2022	en