Title :
Identification of a MISO third-order PARAFAC volterra model
Author :
Nabiha, Saidi ; Messaoud, Hassani
Author_Institution :
Unite de Rech. ATSI, Ecole Nat. d´Ing. de Monastir, Monastir, Tunisia
Abstract :
Volterra models are used to describe non linear systems by models linear with respect to their parameters known as the Volterra kernels. This paper, which is an extension of works proposed in SISO models, is concerned with the problem of identification of a third-order Volterra MISO models. To overcome the burden caused by the huge number of parameters associated to such model, each Volterra kernel is assumed to a tensor which can be split into three matrices using PARAFAC (PARAllel FACtor) decomposition to yield significantly reduced parametric complexity model.
Keywords :
Volterra series; identification; matrix algebra; nonlinear control systems; reduced order systems; tensors; MISO third-order PARAFAC Volterra model identification; Volterra kernels; matrices; nonlinear systems; parallel factor decomposition; reduced parametric complexity model; tensor; Biological system modeling; Complexity theory; Kernel; Linear systems; Linearity; Matrix decomposition; Tensile stress;
Conference_Titel :
Control Conference (ECC), 2009 European
Conference_Location :
Budapest
Print_ISBN :
978-3-9524173-9-3