Kernel-based identification with frequency domain side-information

Kernel-based identification with frequency domain side-information

Khosravi, M. (TU Delft Team Tamas Keviczky)
Smith, Roy S. (ETH Zürich)

2023

This paper discusses the problem of system identification when frequency domain side-information is available. We mainly consider the case where the side-information is provided as the H_∞-norm of the system being bounded by a given scalar. This framework allows considering different forms of frequency domain side-information, such as the dissipativity of the system. We propose a nonparametric identification approach for estimating the impulse response of the system under the given side-information. The estimation problem is formulated as a constrained optimization in a stable reproducing kernel Hilbert space, where suitable constraints are considered for incorporating the desired frequency domain features. The resulting optimization has an infinite-dimensional feasible set with an infinite number of constraints. We show that this problem is a well-defined convex program with a unique solution. We propose a heuristic that tightly approximates this unique solution. The proposed approach is equivalent to solving a finite-dimensional convex quadratically constrained quadratic program. The efficiency of the discussed method is verified by several numerical examples.

Frequency domain properties
Kernel-based methods
Optimization
Side-information
System identification

http://resolver.tudelft.nl/uuid:990604d2-56ea-4215-9fd3-655282964f2c

https://doi.org/10.1016/j.automatica.2022.110813

0005-1098

Automatica, 150

Institutional Repository

journal article

© 2023 M. Khosravi, Roy S. Smith