Least Costly Space-Filling Experiment Design for the Identification of a Nonlinear System
For practitioners in nonlinear system identification, this method reduces experimental cost while preserving data quality, though it is an incremental improvement over existing space-filling designs.
The paper proposes a space-filling input design method for nonlinear system identification that minimizes experimentation cost while maintaining a prescribed level of space-fillingness. Monte Carlo simulations show significant cost reduction with adequate model performance.
The quality of an estimated nonlinear model highly depends on the data quality that was used for the system identification. By using a Gaussian Process-based optimal input design approach, a so-called space-filling dataset can be generated in the feature space of the system model. The design method is applicable for a broad type of signals and models and also incorporates information measures through optimality criteria into the signal design. However, the resulting input design can be costly to apply to the real system. The goal of this paper is to propose a space-filling input design that can minimize the experimentation cost in terms of a user defined measure, while still guaranteeing a prescribed level of space-fillingness. Through a Monte Carlo simulation study we demonstrate that the proposed method can appropriately shape the excitation signal to significantly reduce the experimental cost while the identified model performance remains adequate.