Identification of the Smallest Unfalsified Model Set Based on Stochastic Noisy Data
Toshiharu SUGIE, Hiroaki FUKUSHIMA
In this paper, we propose a new model set identification method using experimental data contaminated by stochastic noise. This method consists of two steps. In the first step, we separate the output error into the deterministic part due to the unmodelled dynamics and the stochastic noise part. In the second step, we find the smallest model set which is consistent with the deterministic part of the experimental data. Furthermore, the effectiveness of this method is shown by numerical examples.