WSEAS Transactions on Power Systems
Print ISSN: 1790-5060, E-ISSN: 2224-350X
Volume 12, 2017
A Nonlinear Thermal Process Modeling and Identification Using a Fourth-Order S-PARAFAC Volterra Model
Authors: , ,
Abstract: This paper proposes a new reduced complexity Volterra model called S-PARAFAC-Volterra. The proposed model is yielded by using the symmetry property of the Volterra kernels and their tensor decomposition using the PARAFAC technique. It takes advantage from previous results where an algorithm for the estimation of the memory and the order of the Volterra model has been presented. The proposed model has been tested to yield a suitable modeling for the nonlinear thermal process Trainer PT326 and the validation results are satisfactory.