Recursive Experiment Design for Closed-Loop Identification with Output Perturbation Limits

TL;DR

This paper presents a method for designing online experiments for ARMAX models that ensures output perturbations stay within specified limits, enhancing safety and efficiency in system identification.

Contribution

It introduces a closed-form, computationally efficient approach for experiment design under output perturbation constraints in closed-loop system identification.

Findings

Method effectively constrains output perturbations.

Closed-form solution enables real-time experiment design.

Numerical experiments demonstrate improved identification accuracy.

Abstract

In many applications, system identification experiments must be performed under output feedback to ensure safety or to maintain system operation. In this paper, we consider the online design of informative experiments for ARMAX models by applying a bounded perturbation to the input signal generated by a fixed output feedback controller. Specifically, the design constrains the resulting output perturbation within user-specified limits and can be efficiently computed in closed form. We demonstrate the effectiveness of the method in a numerical experiment.