Identification of continuous-time MIMO systems via sampled data

In this paper, we present an identification algorithm for continuous-time multiple-input multiple-output (MIMO) state-space models and also for determining the order of models from the samples of the input-output data. In the algorithm, from the sampled data first an equivalent discrete-time model is identified, then the model is converted to the corresponding continuous-time model. The parametric discrete-time canonical-formed MIMO state-space model is identified based on maximum-likelihood and Akaike's information criterion. For obtaining the maximum-likelihood estimates of the model parameters, we apply expectation-maximization algorithms which are iterative methods that are sensitive to the initial estimates. The initial estimates of parameters in canonical-formed state-space models are obtained by MOESP, N4SID or another subspace method where the similarity transformation plays a key role.