Low-rank tensor recovery for Jacobian-based Volterra identification of parallel Wiener-Hammerstein systems. Issue 7 (2021)

• Record Type: Journal Article
• Authors: Usevich, Konstantin; Dreesen, Philippe; Ishteva, Mariya
• Is Part Of: IFAC-PapersOnLine. Volume 54:Issue 7(2021)
• Page Start: 463
• Page End: 468
• Publication Date: 2021
• Subjects: Block structured system identification -- parallel Wiener-Hammerstein systems -- Volterra kernels -- low-rank tensor recovery -- canonical polyadic decomposition; Automatic control -- Periodicals; 629.805
• DOI: 10.1016/j.ifacol.2021.08.403
• Languages: English
• ISSNs: 2405-8963

Abstract

Abstract: We consider the problem of identifying a parallel Wiener-Hammerstein structure from Volterra kernels. Methods based on Volterra kernels typically resort to coupled tensor decompositions of the kernels. However, in the case of parallel Wiener-Hammerstein systems, such methods require nontrivial constraints on the factors of the decompositions. In this paper, we propose an entirely different approach: by using special sampling (operating) points for the Jacobian of the nonlinear map from past inputs to the output, we can show that the Jacobian matrix becomes a linear projection of a tensor whose rank is equal to the number of branches. This representation allows us to solve the identification problem as a tensor recovery problem.