A center-manifold-based system identification method can accurately identify polynomial nonlinear systems with uncontrollable linearization, even in the presence of measurement noise.
The quadratic prediction error method, also known as nonlinear least squares, can achieve optimal non-asymptotic rates of convergence for a wide range of time-varying parametric predictor models satisfying certain identifiability conditions.
Under sub-Gaussian colored noise and stability assumptions, the ETFE estimates are concentrated around the true frequency response values, with an error rate of O((du + √dudy)√M/Ntot), where Ntot is the total number of samples, M is the number of desired frequencies, and du, dy are the dimensions of the input and output signals.
The author proposes a direct approach based on maximum likelihood estimation to identify dynamic networks with missing data, transforming the problem into a more tractable form by leveraging knowledge about network interconnections.
The author proposes a method for identifying linear and nonlinear state-space models using the L-BFGS-B algorithm, showcasing improved results over classical methods and applicability to a broad range of models.