Print Email Facebook Twitter Recursive Kronecker-based Vector AutoRegressive identification for large-scale adaptive optics Title Recursive Kronecker-based Vector AutoRegressive identification for large-scale adaptive optics Author Monchen, Guido (Student TU Delft) Sinquin, B. (TU Delft Team Raf Van de Plas) Verhaegen, M.H.G. (TU Delft Team Raf Van de Plas) Date 2018 Abstract This brief presents an algorithm for the recursive identification of Vector AutoRegressive (VAR) models of large dimensions. We consider a VAR model where the coefficient matrices can be written as a sum of Kronecker products. The algorithm proposed consists of recursively updating the Kronecker factor matrices at each new time step using alternating least squares. When the number of terms in the Kronecker sum is small, a significant reduction in computational complexity is achieved with respect to the recursive least squares algorithm on an unstructured VAR model. Numerical validation of nonstationary atmospheric turbulence data, both synthetic and experimental, is shown for an adaptive optics application. Significant improvements in accuracy over batch identification methods that assume stationarity are observed while both the computational complexity and the required storage are reduced. Subject Kronecker productlarge-scale systemsrecursive least-squares (RLSs)system identificationvector autoregressive (VAR). To reference this document use: http://resolver.tudelft.nl/uuid:bb1037f7-72b0-4ab7-be4d-d0c32bcfd2f5 DOI https://doi.org/10.1109/TCST.2018.2834521 ISSN 1063-6536 Source IEEE Transactions on Control Systems Technology, 27 (July 2019) (4), 1677-1684 Part of collection Institutional Repository Document type journal article Rights © 2018 Guido Monchen, B. Sinquin, M.H.G. Verhaegen Files PDF 08412743.pdf 1.7 MB Close viewer /islandora/object/uuid:bb1037f7-72b0-4ab7-be4d-d0c32bcfd2f5/datastream/OBJ/view