An asymptotically optimal indirect approach to continuous-time system\n identification

2018/03/22 by Rodrigo A. González, González, Rodrigo A., Cristian R. Rojas +3
Computer Science · Engineering · #Control Systems and Identification #FOS: Electrical engineering #Fault Detection and Control Systems #Systems and Control (eess.SY) #Target Tracking and Data Fusion in Sensor Networks #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.1803.08449

openalex publication_date 2018/03/22 · openalex created_date 2022/10/02 · openalex updated_date 2026/07/28

Abstract

The indirect approach to continuous-time system identification consists in\nestimating continuous-time models by first determining an appropriate\ndiscrete-time model. For a zero-order hold sampling mechanism, this approach\nusually leads to a transfer function estimate with relative degree 1,\nindependent of the relative degree of the strictly proper real system. In this\npaper, a refinement of these methods is developed. Inspired by indirect PEM, we\npropose a method that enforces a fixed relative degree in the continuous-time\ntransfer function estimate, and show that the resulting estimator is consistent\nand asymptotically efficient. Extensive numerical simulations are put forward\nto show the performance of this estimator when contrasted with other indirect\nand direct methods for continuous-time system identification.\n

Related

• On the Relation between Discrete and Continuous-time Refined Instrumental Variable Methods
• A Sampling Theorem for Exact Identification of Continuous-time Nonlinear Dynamical Systems
• Finite Sample Analyses for Continuous-time Linear Systems: System Identification and Online Control
• Direct closed-loop identification of continuous-time systems using fixed-pole observer model
• Consistent identification of continuous-time systems under multisine input signal excitation