A Kernel Subspace Method by Stochastic Realization for Learning Nonlinear Dynamical Systems
نویسندگان
چکیده
In this paper, we present a subspace method for learning nonlinear dynamical systems based on stochastic realization, in which state vectors are chosen using kernel canonical correlation analysis, and then state-space systems are identified through regression with the state vectors. We construct the theoretical underpinning and derive a concrete algorithm for nonlinear identification. The obtained algorithm needs no iterative optimization procedure and can be implemented on the basis of fast and reliable numerical schemes. The simulation result shows that our algorithm can express dynamics with a high degree of accuracy.
منابع مشابه
Model Reduction for Nonlinear Control Systems using Kernel Subspace Methods
We introduce a data-driven model approximation method for nonlinear control systems, drawing on recent progress in machine learning and statistical dimensionality reduction. The method is based on embedding the nonlinear system in a high (or infinite) dimensional reproducing kernel Hilbert space (RKHS) where linear balanced truncation may be carried out implicitly. This leads to a nonlinear red...
متن کاملDetermination of Stability Domains for Nonlinear Dynamical Systems Using the Weighted Residuals Method
Finding a suitable estimation of stability domain around stable equilibrium points is an important issue in the study of nonlinear dynamical systems. This paper intends to apply a set of analytical-numerical methods to estimate the region of attraction for autonomous nonlinear systems. In mechanical and structural engineering, autonomous systems could be found in large deformation problems or c...
متن کاملDynamical Control of Computations Using the Family of Optimal Two-point Methods to Solve Nonlinear Equations
One of the considerable discussions for solving the nonlinear equations is to find the optimal iteration, and to use a proper termination criterion which is able to obtain a high accuracy for the numerical solution. In this paper, for a certain class of the family of optimal two-point methods, we propose a new scheme based on the stochastic arithmetic to find the optimal number of iterations in...
متن کاملSubspace Identification of Closed Loop Systems by Stochastic Realization
We develop a closed loop subspace identification method based on stochastic realization theory. Using the preliminary orthogonal decomposition of (Picci and Katayama, 1996b) we show that, under the assumption that the exogenous input is feedback-free and persistently exciting (PE), the identification of closed loop systems is divided into two subproblems: the deterministic identification of the...
متن کاملAn Algorithm for Multi-Realization of Nonlinear MIMO Systems
This paper presents a theoretical approach to implementation of the “Multi-realization of nonlinear MIMO systems”. This method aims to find state-variable realization for a set of systems, sharing as many parameters as possible. In this paper a special nonlinear multi-realization problem, namely the multi-realization of feedback linearizable nonlinear systems is considered and an algorithm for ...
متن کامل