Multi-objective Optimization Approach to Optimal Input Design for Autoregressive Model Identification
| Authors: | Uosaki Katsuji, Osaka University, Japan
Hatanaka Toshiharu, Osaka University, Japan |
|---|
| Topic: | 1.1 Modelling, Identification & Signal Processing |
|---|
| Session: | Input Design |
|---|
| Keywords: | System identification, Optimal experimental design, System structure, Parameter estimation, Multi-objective optimizations, Pareto-optimal solution |
|---|
Abstract
Optimality criteria of the experimental design in dynamic system identification may sometimes be conflicting for structure determination and parameter estimation steps. This leads the necessity of the tradeoffs between the performances in these two steps. Here, the optimal input design in system identification is investigated as a multi-objective optimization problem. The Pareto-optimal set of inputs is derived and how to use it in system identification is discussed.
