Identification of Fast-rate Nonlinear Output Error Models From Multi-rate Data

This work aims at the identification of a nonlinear fast rate model from multi-rate sampled data, which is corrupted with unmeasured disturbances and measurement noise. The model identification is carried out in two steps. In the first step, a MISO fast rate nonlinear output error (NOE) model with Weiner structure is identified from the multi-rate data. In the next step, a nonlinear auto regressive (NAR) model is developed, which whitens the residuals. The efficacy of the proposed modeling scheme is demonstrated by carrying out simulation studies on a CSTR system, which exhibits input multiplicities and change in the sign of the steady state gain in the desired operating region. The analysis of the simulation results reveals that the proposed multi rate models are able to capture the dynamics and the steady state behavior of the reactor reasonably accurately over a wide operating range.